Model Gallery
Discover and install AI models from our curated collection
Find Your Perfect Model
Filter by Model Type
Browse by Tags
qwen3.8-flash-next-ista-q2_0
Qwen3.8-Flash-Next, a 125B-parameter hybrid mixture-of-experts model, in
ISTA-DASLab's 2-bit GSQ-RCO quantization (Q2_0), the fastest size (about 67 GB
to download).
It reads images through the vision projector published for the original model,
and the Strata backend parses its reasoning and tool calls.
Needs about 38 GB of RAM and VRAM together for the model (34 GB of experts in
RAM plus about 10 GB for the system), and fast SSD storage: the 29 GB n-gram
table stays on disk. Needs a GPU the strata backend supports; NVIDIA with 12
GB of VRAM or more is the class Strata tests. Runs only on the experimental
strata backend.
On the first load the strata backend builds the Strata pack from the GGUF
files (a few minutes, a few GB of extra disk); a finished pack is never
rebuilt. The experts are read from the GGUF files in place (mapped); add
--resident-experts to engine_args to copy them into RAM when there is room.
Licensed under the Qwen Community License 1.0 (inherited from
Qwen/Qwen3.8-Flash-Next): free use, but a Model as a Service or AI Work
Assistant business needs a licence from Qwen. Read the LICENSE file in the
repository first.
The GGUF files are the GSQ-RCO quantization by ISTA-DASLab; Strata is by
Niko1221. The MTP draft layer is not configured here.
Repository: localaiLicense: qwen-community-1.0
qwen3.8-flash-next-ista-iq2_xs
Qwen3.8-Flash-Next, a 125B-parameter hybrid mixture-of-experts model, in
ISTA-DASLab's 2-bit i-quant GSQ-RCO quantization (IQ2_XS), a little better
than Q2_0 at close speed (about 69 GB to download).
It reads images through the vision projector published for the original model,
and the Strata backend parses its reasoning and tool calls.
Needs about 39 GB of RAM and VRAM together for the model (35.5 GB of experts
in RAM plus about 10 GB for the system), and fast SSD storage: the 29 GB
n-gram table stays on disk. Needs a GPU the strata backend supports; NVIDIA
with 12 GB of VRAM or more is the class Strata tests. Runs only on the
experimental strata backend.
On the first load the strata backend builds the Strata pack from the GGUF
files (a few minutes, a few GB of extra disk); a finished pack is never
rebuilt. The experts are read from the GGUF files in place (mapped); add
--resident-experts to engine_args to copy them into RAM when there is room.
Licensed under the Qwen Community License 1.0 (inherited from
Qwen/Qwen3.8-Flash-Next): free use, but a Model as a Service or AI Work
Assistant business needs a licence from Qwen. Read the LICENSE file in the
repository first.
The GGUF files are the GSQ-RCO quantization by ISTA-DASLab; Strata is by
Niko1221. The MTP draft layer is not configured here.
Repository: localaiLicense: qwen-community-1.0
qwen3.8-flash-next-ista-iq3_xxs
Qwen3.8-Flash-Next, a 125B-parameter hybrid mixture-of-experts model, in
ISTA-DASLab's 3-bit i-quant GSQ-RCO quantization (IQ3_XXS), better quality and
slower (about 77 GB to download).
It reads images through the vision projector published for the original model,
and the Strata backend parses its reasoning and tool calls.
Needs about 47 GB of RAM and VRAM together for the model (43 GB of experts in
RAM plus about 10 GB for the system), and fast SSD storage: the 29 GB n-gram
table stays on disk. Needs a GPU the strata backend supports; NVIDIA with 12
GB of VRAM or more is the class Strata tests. Runs only on the experimental
strata backend.
On the first load the strata backend builds the Strata pack from the GGUF
files (a few minutes, a few GB of extra disk); a finished pack is never
rebuilt. The experts are read from the GGUF files in place (mapped); add
--resident-experts to engine_args to copy them into RAM when there is room.
Licensed under the Qwen Community License 1.0 (inherited from
Qwen/Qwen3.8-Flash-Next): free use, but a Model as a Service or AI Work
Assistant business needs a licence from Qwen. Read the LICENSE file in the
repository first.
The GGUF files are the GSQ-RCO quantization by ISTA-DASLab; Strata is by
Niko1221. The MTP draft layer is not configured here.
Repository: localaiLicense: qwen-community-1.0
qwen3.8-flash-next-ista-iq3_s
Qwen3.8-Flash-Next, a 125B-parameter hybrid mixture-of-experts model, in
ISTA-DASLab's 3.5-bit i-quant GSQ-RCO quantization (IQ3_S), the best quality
of the four, matching the full model on the published tests, and the slowest
(about 85 GB to download).
It reads images through the vision projector published for the original model,
and the Strata backend parses its reasoning and tool calls.
Needs about 55 GB of RAM and VRAM together for the model (50 GB of experts in
RAM plus about 10 GB for the system; a 64 GB machine with little else
running), and fast SSD storage: the 29 GB n-gram table stays on disk. Needs a
GPU the strata backend supports; NVIDIA with 12 GB of VRAM or more is the
class Strata tests. Runs only on the experimental strata backend.
On the first load the strata backend builds the Strata pack from the GGUF
files (a few minutes, a few GB of extra disk); a finished pack is never
rebuilt. The experts are read from the GGUF files in place (mapped); add
--resident-experts to engine_args to copy them into RAM when there is room.
Licensed under the Qwen Community License 1.0 (inherited from
Qwen/Qwen3.8-Flash-Next): free use, but a Model as a Service or AI Work
Assistant business needs a licence from Qwen. Read the LICENSE file in the
repository first.
The GGUF files are the GSQ-RCO quantization by ISTA-DASLab; Strata is by
Niko1221. The MTP draft layer is not configured here.
Repository: localaiLicense: qwen-community-1.0
qwen3.8-flash-next-coder-iq1_m
Qwen3.8-Flash-Next, a 125B-parameter hybrid mixture-of-experts model, in
ISTA-DASLab's Coder release (IQ1_M): half of the experts (256 of 512 per
layer) are kept, chosen on code, agent and image data, so it is smaller and
faster but weaker outside code and in languages other than English (Chinese
and other CJK text included) (about 59 GB to download).
It reads images through the vision projector published for the original model,
and the Strata backend parses its reasoning and tool calls.
Needs about 32 GB of RAM (23 GB of experts in RAM) with a suitable GPU, and
fast SSD storage: the 29 GB n-gram table stays on disk. Needs a GPU the strata
backend supports; NVIDIA with 12 GB of VRAM or more is the class Strata tests.
Runs only on the experimental strata backend.
On the first load the strata backend builds the Strata pack from the GGUF
files (a few minutes, a few GB of extra disk); a finished pack is never
rebuilt. The experts are read from the GGUF files in place (mapped); add
--resident-experts to engine_args to copy them into RAM when there is room.
Licensed under the Qwen Community License 1.0 (inherited from
Qwen/Qwen3.8-Flash-Next): free use, but a Model as a Service or AI Work
Assistant business needs a licence from Qwen. Read the LICENSE file in the
repository first.
The GGUF files are the Coder GSQ-RCO quantization by ISTA-DASLab; Strata is by
Niko1221. The MTP draft layer is not configured here.
Repository: localaiLicense: qwen-community-1.0
swift-1.5-qwen3.8-flash-next-iq2_xs
Qwen3.8-Flash-Next, a 125B-parameter hybrid mixture-of-experts model, in
UkisAI's Swift 1.5 fine-tune, which thinks much shorter before it answers, at
2-bit i-quant (IQ2_XS) (about 69 GB to download).
It reads images through the vision projector published for the original model,
and the Strata backend parses its reasoning and tool calls.
Needs about 39 GB of RAM and VRAM together for the model (the same as the same
size of the original), and fast SSD storage for the n-gram table. Needs a GPU
the strata backend supports; NVIDIA with 12 GB of VRAM or more is the class
Strata tests. Runs only on the experimental strata backend.
On the first load the strata backend builds the Strata pack from the GGUF
files (a few minutes, a few GB of extra disk); a finished pack is never
rebuilt. The experts are read from the GGUF files in place (mapped); add
--resident-experts to engine_args to copy them into RAM when there is room.
Two licences apply: UkisAI's Swift Open License 1.0 for the fine-tune, and the
Qwen Community License 1.0 for the Qwen3.8-Flash-Next parts it is built from.
Read both before you offer the model to other people.
The GGUF files are the quantization by UkisAI of its Swift 1.5 fine-tune;
Strata is by Niko1221. The MTP draft layer is not configured here.
Repository: localaiLicense: swift-open-license-1.0
swift-1.5-qwen3.8-flash-next-iq3_xxs
Qwen3.8-Flash-Next, a 125B-parameter hybrid mixture-of-experts model, in
UkisAI's Swift 1.5 fine-tune, which thinks much shorter before it answers, at
3-bit i-quant (IQ3_XXS) (about 77 GB to download).
It reads images through the vision projector published for the original model,
and the Strata backend parses its reasoning and tool calls.
Needs about 47 GB of RAM and VRAM together for the model (the same as the same
size of the original), and fast SSD storage for the n-gram table. Needs a GPU
the strata backend supports; NVIDIA with 12 GB of VRAM or more is the class
Strata tests. Runs only on the experimental strata backend.
On the first load the strata backend builds the Strata pack from the GGUF
files (a few minutes, a few GB of extra disk); a finished pack is never
rebuilt. The experts are read from the GGUF files in place (mapped); add
--resident-experts to engine_args to copy them into RAM when there is room.
Two licences apply: UkisAI's Swift Open License 1.0 for the fine-tune, and the
Qwen Community License 1.0 for the Qwen3.8-Flash-Next parts it is built from.
Read both before you offer the model to other people.
The GGUF files are the quantization by UkisAI of its Swift 1.5 fine-tune;
Strata is by Niko1221. The MTP draft layer is not configured here.
Repository: localaiLicense: swift-open-license-1.0
swift-1.5-qwen3.8-flash-next-iq3_s
Qwen3.8-Flash-Next, a 125B-parameter hybrid mixture-of-experts model, in
UkisAI's Swift 1.5 fine-tune, which thinks much shorter before it answers, at
3.5-bit i-quant (IQ3_S) (about 85 GB to download).
It reads images through the vision projector published for the original model,
and the Strata backend parses its reasoning and tool calls.
Needs about 55 GB of RAM and VRAM together for the model (the same as the same
size of the original), and fast SSD storage for the n-gram table. Needs a GPU
the strata backend supports; NVIDIA with 12 GB of VRAM or more is the class
Strata tests. Runs only on the experimental strata backend.
On the first load the strata backend builds the Strata pack from the GGUF
files (a few minutes, a few GB of extra disk); a finished pack is never
rebuilt. The experts are read from the GGUF files in place (mapped); add
--resident-experts to engine_args to copy them into RAM when there is room.
Two licences apply: UkisAI's Swift Open License 1.0 for the fine-tune, and the
Qwen Community License 1.0 for the Qwen3.8-Flash-Next parts it is built from.
Read both before you offer the model to other people.
The GGUF files are the quantization by UkisAI of its Swift 1.5 fine-tune;
Strata is by Niko1221. The MTP draft layer is not configured here.
Repository: localaiLicense: swift-open-license-1.0
qwen3.8-flash-next-unsloth-ud-iq4_xs
Qwen3.8-Flash-Next, a 125B-parameter hybrid mixture-of-experts model, in
Unsloth's Dynamic quantization (UD-IQ4_XS, about 4-bit i-quant) (about 95 GB
to download).
It reads images through the vision projector published for the original model,
and the Strata backend parses its reasoning and tool calls.
Needs about 72 GB of RAM to keep every expert in memory; with less, the mapped
experts are read from the SSD while it answers, which works and is much
slower. Keep the files on an SSD. Needs a GPU the strata backend supports;
NVIDIA with 12 GB of VRAM or more is the class Strata tests. Runs only on the
experimental strata backend.
On the first load the strata backend builds the Strata pack from the GGUF
files (a few minutes, a few GB of extra disk); a finished pack is never
rebuilt. The experts are read from the GGUF files in place (mapped); add
--resident-experts to engine_args to copy them into RAM when there is room.
Licensed under the Qwen Community License 1.0 (inherited from
Qwen/Qwen3.8-Flash-Next): free use, but a Model as a Service or AI Work
Assistant business needs a licence from Qwen. Read the LICENSE file in the
repository first.
The GGUF files are the Unsloth quantization; the vision projector is
ISTA-DASLab's file for the original model; Strata is by Niko1221. The MTP
draft layer is not configured here.
Repository: localaiLicense: qwen-community-1.0
qwen3.8-flash-next-unsloth-ud-q4_k_xl
Qwen3.8-Flash-Next, a 125B-parameter hybrid mixture-of-experts model, in
Unsloth's Dynamic quantization (UD-Q4_K_XL, 4-bit) (about 112 GB to download).
It reads images through the vision projector published for the original model,
and the Strata backend parses its reasoning and tool calls.
Needs about 88 GB of RAM to keep every expert in memory; with less, the mapped
experts are read from the SSD while it answers, which works and is much
slower. Keep the files on an SSD. Needs a GPU the strata backend supports;
NVIDIA with 12 GB of VRAM or more is the class Strata tests. Runs only on the
experimental strata backend.
On the first load the strata backend builds the Strata pack from the GGUF
files (a few minutes, a few GB of extra disk); a finished pack is never
rebuilt. The experts are read from the GGUF files in place (mapped); add
--resident-experts to engine_args to copy them into RAM when there is room.
Licensed under the Qwen Community License 1.0 (inherited from
Qwen/Qwen3.8-Flash-Next): free use, but a Model as a Service or AI Work
Assistant business needs a licence from Qwen. Read the LICENSE file in the
repository first.
The GGUF files are the Unsloth quantization; the vision projector is
ISTA-DASLab's file for the original model; Strata is by Niko1221. The MTP
draft layer is not configured here.
Repository: localaiLicense: qwen-community-1.0
qwen3.8-flash-next-unsloth-ud-q5_k_xl
Qwen3.8-Flash-Next, a 125B-parameter hybrid mixture-of-experts model, in
Unsloth's Dynamic quantization (UD-Q5_K_XL, 5-bit, close to Q8_0) (about 159
GB to download).
It reads images through the vision projector published for the original model,
and the Strata backend parses its reasoning and tool calls.
Needs about 108 GB of RAM to keep every expert in memory; with less, the
mapped experts are read from the SSD while it answers, which works and is much
slower. Keep the files on an SSD. Needs a GPU the strata backend supports;
NVIDIA with 12 GB of VRAM or more is the class Strata tests. Runs only on the
experimental strata backend.
On the first load the strata backend builds the Strata pack from the GGUF
files (a few minutes, a few GB of extra disk); a finished pack is never
rebuilt. The experts are read from the GGUF files in place (mapped); add
--resident-experts to engine_args to copy them into RAM when there is room.
Licensed under the Qwen Community License 1.0 (inherited from
Qwen/Qwen3.8-Flash-Next): free use, but a Model as a Service or AI Work
Assistant business needs a licence from Qwen. Read the LICENSE file in the
repository first.
The GGUF files are the Unsloth quantization; the vision projector is
ISTA-DASLab's file for the original model; Strata is by Niko1221. The MTP
draft layer is not configured here.
Repository: localaiLicense: qwen-community-1.0
qwen3.8-flash-next-unsloth-ud-q6_k_xl
Qwen3.8-Flash-Next, a 125B-parameter hybrid mixture-of-experts model, in
Unsloth's Dynamic quantization (UD-Q6_K_XL, 6-bit) (about 170 GB to download).
It reads images through the vision projector published for the original model,
and the Strata backend parses its reasoning and tool calls.
Needs about 118 GB of RAM to keep every expert in memory; with less, the
mapped experts are read from the SSD while it answers, which works and is much
slower. Keep the files on an SSD. Needs a GPU the strata backend supports;
NVIDIA with 12 GB of VRAM or more is the class Strata tests. Runs only on the
experimental strata backend.
On the first load the strata backend builds the Strata pack from the GGUF
files (a few minutes, a few GB of extra disk); a finished pack is never
rebuilt. The experts are read from the GGUF files in place (mapped); add
--resident-experts to engine_args to copy them into RAM when there is room.
Licensed under the Qwen Community License 1.0 (inherited from
Qwen/Qwen3.8-Flash-Next): free use, but a Model as a Service or AI Work
Assistant business needs a licence from Qwen. Read the LICENSE file in the
repository first.
The GGUF files are the Unsloth quantization; the vision projector is
ISTA-DASLab's file for the original model; Strata is by Niko1221. The MTP
draft layer is not configured here.
Repository: localaiLicense: qwen-community-1.0
qwen3.8-flash-next-unsloth-q8_0
Qwen3.8-Flash-Next, a 125B-parameter hybrid mixture-of-experts model, in
Unsloth's Dynamic quantization (Q8_0, 8-bit, the reference quality) (about 189
GB to download).
It reads images through the vision projector published for the original model,
and the Strata backend parses its reasoning and tool calls.
Needs about 136 GB of RAM to keep every expert in memory; with less, the
mapped experts are read from the SSD while it answers, which works and is much
slower. Keep the files on an SSD. Needs a GPU the strata backend supports;
NVIDIA with 12 GB of VRAM or more is the class Strata tests. Runs only on the
experimental strata backend.
On the first load the strata backend builds the Strata pack from the GGUF
files (a few minutes, a few GB of extra disk); a finished pack is never
rebuilt. The experts are read from the GGUF files in place (mapped); add
--resident-experts to engine_args to copy them into RAM when there is room.
Licensed under the Qwen Community License 1.0 (inherited from
Qwen/Qwen3.8-Flash-Next): free use, but a Model as a Service or AI Work
Assistant business needs a licence from Qwen. Read the LICENSE file in the
repository first.
The GGUF files are the Unsloth quantization; the vision projector is
ISTA-DASLab's file for the original model; Strata is by Niko1221. The MTP
draft layer is not configured here.
Repository: localaiLicense: qwen-community-1.0
qwen3.8-flash-next-gyro-s
Qwen3.8-Flash-Next, a 125B-parameter hybrid mixture-of-experts model, in
agentionai's Gyro-S quantization (trellis-coded experts), the smallest option,
for machines with little memory and lower in quality (about 59 GB to
download).
It reads images through the vision projector published for the original model,
and the Strata backend parses its reasoning and tool calls.
Needs about 28 GB of VRAM and RAM together for the weights. Half of the file
is the n-gram table, which stays on disk and is read for every token, so keep
it on a fast local SSD. Needs a GPU the strata backend supports; NVIDIA with
12 GB of VRAM or more is the class Strata tests. Runs only on the experimental
strata backend.
On the first load the strata backend builds the Strata pack from the GGUF
files (a few minutes, a few GB of extra disk); a finished pack is never
rebuilt. The experts are read from the GGUF files in place (mapped); add
--resident-experts to engine_args to copy them into RAM when there is room.
Licensed under the Qwen Community License 1.0 (inherited from
Qwen/Qwen3.8-Flash-Next): free use, but a Model as a Service or AI Work
Assistant business needs a licence from Qwen. Read the LICENSE file in the
repository first.
The GGUF file is the Gyro quantization by agentionai; the vision projector is
ISTA-DASLab's file for the original model; Strata is by Niko1221. The MTP
draft layer is not configured here.
Repository: localaiLicense: qwen-community-1.0
qwen3.8-flash-next-gyro-m
Qwen3.8-Flash-Next, a 125B-parameter hybrid mixture-of-experts model, in
agentionai's Gyro-M quantization (trellis-coded experts), about IQ3_XXS
quality with about 20% less GPU memory, 16 to 21% slower than Q2_0 (about 93
GB to download).
It reads images through the vision projector published for the original model,
and the Strata backend parses its reasoning and tool calls.
Needs about 35 GB of VRAM and RAM together for the weights. Half of the file
is the n-gram table, which stays on disk and is read for every token, so keep
it on a fast local SSD. Needs a GPU the strata backend supports; NVIDIA with
12 GB of VRAM or more is the class Strata tests. Runs only on the experimental
strata backend.
On the first load the strata backend builds the Strata pack from the GGUF
files (a few minutes, a few GB of extra disk); a finished pack is never
rebuilt. The experts are read from the GGUF files in place (mapped); add
--resident-experts to engine_args to copy them into RAM when there is room.
Licensed under the Qwen Community License 1.0 (inherited from
Qwen/Qwen3.8-Flash-Next): free use, but a Model as a Service or AI Work
Assistant business needs a licence from Qwen. Read the LICENSE file in the
repository first.
The GGUF file is the Gyro quantization by agentionai; the vision projector is
ISTA-DASLab's file for the original model; Strata is by Niko1221. The MTP
draft layer is not configured here.
Repository: localaiLicense: qwen-community-1.0
qwen3.6-35b-a3b-ud-q4_k_xl-strata
Qwen3.6-35B-A3B, a 35B-parameter mixture-of-experts model with 3B active
parameters, in Unsloth's 4-bit (Unsloth Dynamic), the smallest GGUF with the
MTP layer (about 24 GB to download). It reads images through Unsloth's vision
projector, and the Strata backend parses its reasoning and tool calls.
Needs an NVIDIA or AMD GPU (the Intel Arc and Apple builds of Strata do not
run this model) and about 32 GB of RAM: the engine keeps every expert it can
in VRAM and computes the rest on the CPU. Runs only on the experimental strata
backend.
On the first load the strata backend exports the tokenizer and chat template
from the GGUF file (seconds); the engine reads the GGUF as it is. The MTP
draft layer inside the file is used for speculative decoding.
Licensed under the Apache License 2.0 (Qwen/Qwen3.6-35B-A3B). The GGUF files
are the Unsloth quantization; Strata is by Niko1221.
Repository: localaiLicense: apache-2.0
qwen3.6-35b-a3b-ud-q6_k_xl-strata
Qwen3.6-35B-A3B, a 35B-parameter mixture-of-experts model with 3B active
parameters, in Unsloth's 6-bit (Unsloth Dynamic), closer to the full model
GGUF with the MTP layer (about 34 GB to download). It reads images through
Unsloth's vision projector, and the Strata backend parses its reasoning and
tool calls.
Needs an NVIDIA or AMD GPU (the Intel Arc and Apple builds of Strata do not
run this model) and about 44 GB of RAM: the engine keeps every expert it can
in VRAM and computes the rest on the CPU. Runs only on the experimental strata
backend.
On the first load the strata backend exports the tokenizer and chat template
from the GGUF file (seconds); the engine reads the GGUF as it is. The MTP
draft layer inside the file is used for speculative decoding.
Licensed under the Apache License 2.0 (Qwen/Qwen3.6-35B-A3B). The GGUF files
are the Unsloth quantization; Strata is by Niko1221.
Repository: localaiLicense: apache-2.0
qwen3.6-35b-a3b-q8_0-strata
Qwen3.6-35B-A3B, a 35B-parameter mixture-of-experts model with 3B active
parameters, in Unsloth's 8-bit, the closest to the full model GGUF with the
MTP layer (about 39 GB to download). It reads images through Unsloth's vision
projector, and the Strata backend parses its reasoning and tool calls.
Needs an NVIDIA or AMD GPU (the Intel Arc and Apple builds of Strata do not
run this model) and about 52 GB of RAM: the engine keeps every expert it can
in VRAM and computes the rest on the CPU. Runs only on the experimental strata
backend.
On the first load the strata backend exports the tokenizer and chat template
from the GGUF file (seconds); the engine reads the GGUF as it is. The MTP
draft layer inside the file is used for speculative decoding.
Licensed under the Apache License 2.0 (Qwen/Qwen3.6-35B-A3B). The GGUF files
are the Unsloth quantization; Strata is by Niko1221.
Repository: localaiLicense: apache-2.0
deepseek-v4.1-flash-ista-iq1_m
DeepSeek-V4.1-Flash-1017, a 763B-parameter mixture-of-experts model (384 experts
per layer, 6 used per token), in ISTA-DAS's 1.75 bits per weight GSQ-RCO
quantization (IQ1_M), the smallest size of the three (about 239 GB to download).
It writes a reasoning trace before the answer, and the Strata backend splits it
from the reply and parses the model's DSML tool calls. Text only: images are not
supported by this backend.
Needs a GPU with 12 GB of VRAM or more and about 34 GB of RAM at the least
(Strata's figure; its measurements use 46 to 64 GB: an RTX 5070 with 64 GB
answered at about 5 tokens per second, an RTX 3060 with 46 GB at 8 to 10). Less
RAM still runs, slowly. Slightly lower quality than 2.00 bpw, and noticeably
weaker on plain English prose; ISTA-DASLab measured 98.7% of the base model on
its task average (AIME25, GPQA-Diamond, LiveCodeBench v6).
Needs about 240 GB of free disk, on a fast NVMe drive: the 111 GB n-gram table
(Engram) stays on disk and is read for every token. The Engram table and the 8
GB DSpark draft model are shared by all DeepSeek-V4.1 entries and downloaded
once into strata/models/deepseek-v4.1-flash-shared.
Runs only on the experimental strata backend, on NVIDIA CUDA 13 (x86_64 and
arm64), AMD Radeon RX 9070 and R9700 (ROCm) and Apple Silicon (Metal). Strata
ships no DeepSeek engine for CUDA 12, Intel or other AMD cards.
On the first load the strata backend builds the Strata pack from the GGUF files
(under a minute, a few MB of extra disk); loading the model afterwards takes a
few minutes. The default context is 8192 tokens, the size Strata checked; raise
context_size if the GPU has room.
Licensed under the MIT License (DeepSeek-V4.1-Flash-1017 and the quantized
files). The GGUF files are the GSQ-RCO quantization by ISTA-DAS (ISTA-DASLab);
the DSpark draft model is Unsloth's; Strata is by Niko1221.
Repository: localaiLicense: mit
deepseek-v4.1-flash-ista-iq2_xxs
DeepSeek-V4.1-Flash-1017, a 763B-parameter mixture-of-experts model (384 experts
per layer, 6 used per token), in ISTA-DAS's 2.00 bits per weight GSQ-RCO
quantization (IQ2_XXS), the middle size of the three (about 257 GB to download).
It writes a reasoning trace before the answer, and the Strata backend splits it
from the reply and parses the model's DSML tool calls. Text only: images are not
supported by this backend.
Needs a GPU with 12 GB of VRAM or more and about 40 GB of RAM at the least
(Strata's figure; its measurements use 46 to 64 GB: an RTX 5070 with 64 GB
answered at about 5 tokens per second, an RTX 3060 with 46 GB at 8 to 10). Less
RAM still runs, slowly. Strata measured a perplexity 15.5% above the original
model on 4,995 positions (code 8.6%, agent work 5.3%).
Needs about 258 GB of free disk, on a fast NVMe drive: the 111 GB n-gram table
(Engram) stays on disk and is read for every token. The Engram table and the 8
GB DSpark draft model are shared by all DeepSeek-V4.1 entries and downloaded
once into strata/models/deepseek-v4.1-flash-shared.
Runs only on the experimental strata backend, on NVIDIA CUDA 13 (x86_64 and
arm64), AMD Radeon RX 9070 and R9700 (ROCm) and Apple Silicon (Metal). Strata
ships no DeepSeek engine for CUDA 12, Intel or other AMD cards.
On the first load the strata backend builds the Strata pack from the GGUF files
(under a minute, a few MB of extra disk); loading the model afterwards takes a
few minutes. The default context is 8192 tokens, the size Strata checked; raise
context_size if the GPU has room.
Licensed under the MIT License (DeepSeek-V4.1-Flash-1017 and the quantized
files). The GGUF files are the GSQ-RCO quantization by ISTA-DAS (ISTA-DASLab);
the DSpark draft model is Unsloth's; Strata is by Niko1221.
Repository: localaiLicense: mit
deepseek-v4.1-flash-ista-iq2_xs
DeepSeek-V4.1-Flash-1017, a 763B-parameter mixture-of-experts model (384 experts
per layer, 6 used per token), in ISTA-DAS's 2.25 bits per weight GSQ-RCO
quantization (IQ2_XS), the largest size of the three (about 274 GB to download).
It writes a reasoning trace before the answer, and the Strata backend splits it
from the reply and parses the model's DSML tool calls. Text only: images are not
supported by this backend.
Needs a GPU with 12 GB of VRAM or more and about 44 GB of RAM at the least
(Strata's figure; its measurements use 46 to 64 GB: an RTX 5070 with 64 GB
answered at about 5 tokens per second, an RTX 3060 with 46 GB at 8 to 10). Less
RAM still runs, slowly. Strata measured a perplexity 7.3% above the original
model on 4,995 positions (code 3.2%, agent work 2.2%).
Needs about 275 GB of free disk, on a fast NVMe drive: the 111 GB n-gram table
(Engram) stays on disk and is read for every token. The Engram table and the 8
GB DSpark draft model are shared by all DeepSeek-V4.1 entries and downloaded
once into strata/models/deepseek-v4.1-flash-shared.
Runs only on the experimental strata backend, on NVIDIA CUDA 13 (x86_64 and
arm64), AMD Radeon RX 9070 and R9700 (ROCm) and Apple Silicon (Metal). Strata
ships no DeepSeek engine for CUDA 12, Intel or other AMD cards.
On the first load the strata backend builds the Strata pack from the GGUF files
(under a minute, a few MB of extra disk); loading the model afterwards takes a
few minutes. The default context is 8192 tokens, the size Strata checked; raise
context_size if the GPU has room.
Licensed under the MIT License (DeepSeek-V4.1-Flash-1017 and the quantized
files). The GGUF files are the GSQ-RCO quantization by ISTA-DAS (ISTA-DASLab);
the DSpark draft model is Unsloth's; Strata is by Niko1221.
Repository: localaiLicense: mit
Page
1
of many