Model Gallery
Discover and install AI models from our curated collection
Find Your Perfect Model
Filter by Model Type
Browse by Tags
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
deepseek-v4.1-flash-ista-coder-iq2_xxs
ISTA-DAS's coding version of DeepSeek-V4.1-Flash-1017: in every layer 192 of the
384 routed experts are kept and the other 192 removed, stored in the 2.00 bpw
(IQ2_XXS) layout. It is the smallest DeepSeek-V4.1 set here (about 191 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 24 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 48% above the original
model on its test set (KL 0.40), so it is weaker than the full sets on prose and
general knowledge; it is meant for code and agent work.
Needs about 192 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
spark-x2.6-4b-q4
Spark-X2.6-4B is XHToken's 4B text model for conversation, reasoning,
coding, and multilingual tasks. This build uses Q4_K_M GGUF weights,
the embedded Jinja chat template, and a 32K-token default context.
Repository: localaiLicense: apache-2.0
spark-x2.6-4b-q8
Spark-X2.6-4B is XHToken's 4B text model for conversation, reasoning,
coding, and multilingual tasks. This build uses Q8_0 GGUF weights,
the embedded Jinja chat template, and a 32K-token default context.
Repository: localaiLicense: apache-2.0
ornith-1.5-122b-ud-q4-k-xl
Ornith 1.5 122B is a Qwen3.5 mixture-of-experts model for reasoning,
coding, and tool use. This UD-Q4_K_XL GGUF build includes the F16 vision
projector for image input and uses an 8,192-token default context.
Repository: localaiLicense: mit
ornith-1.5-122b-q8
Ornith 1.5 122B is a Qwen3.5 mixture-of-experts model for reasoning,
coding, and tool use. This Q8_0 GGUF build includes the F16 vision
projector for image input and uses an 8,192-token default context.
Repository: localaiLicense: mit
gemma-4-e2b-it-artemis-q3-k-l
TurinTech Artemis Q3_K_L quantization of Gemma 4 E2B from Google's QAT
checkpoint, for local chat and tool calls. Accepts image input through
the bundled F16 vision projector. Uses the embedded chat template and
an 8192-token context. Thinking is on by default.
Repository: localaiLicense: apache-2.0
gemma-4-e2b-it-artemis-q3-k-m
TurinTech Artemis Q3_K_M quantization of Gemma 4 E2B from Google's QAT
checkpoint, for local chat and tool calls. Accepts image input through
the bundled F16 vision projector. Uses the embedded chat template and
an 8192-token context. Thinking is on by default.
Repository: localaiLicense: apache-2.0
gemma-4-e2b-it-artemis-iq3-xxs
TurinTech Artemis IQ3_XXS quantization of Gemma 4 E2B from Google's QAT
checkpoint, for local chat and tool calls. Accepts image input through
the bundled F16 vision projector. Uses the embedded chat template and
an 8192-token context. Thinking is on by default.
Repository: localaiLicense: apache-2.0
gemma-4-e2b-it-artemis-iq2-m
TurinTech Artemis IQ2_M quantization of Gemma 4 E2B from Google's QAT
checkpoint, for local chat and tool calls. Accepts image input through
the bundled F16 vision projector. Uses the embedded chat template and
an 8192-token context. Thinking is on by default.
Repository: localaiLicense: apache-2.0
gemma-4-e4b-it-artemis-q4-0
TurinTech Artemis Q4_0 quantization of Gemma 4 E4B from Google's QAT
checkpoint, for local chat, reasoning, and tool use. Accepts image
input through the bundled F16 vision projector. Uses the embedded chat
template and an 8192-token context. Thinking is on by default.
Repository: localaiLicense: apache-2.0
gemma-4-e4b-it-artemis-iq3-m
TurinTech Artemis IQ3_M quantization of Gemma 4 E4B from Google's QAT
checkpoint, for local chat, reasoning, and tool use. Accepts image
input through the bundled F16 vision projector. Uses the embedded chat
template and an 8192-token context. Thinking is on by default.
Repository: localaiLicense: apache-2.0
gemma-4-e4b-it-artemis-q3-k-m
TurinTech Artemis Q3_K_M quantization of Gemma 4 E4B from Google's QAT
checkpoint, for local chat, reasoning, and tool use. Accepts image
input through the bundled F16 vision projector. Uses the embedded chat
template and an 8192-token context. Thinking is on by default.
Repository: localaiLicense: apache-2.0
diplodocus-preview-q4
Diplodocus preview 4 is OsaurusAI's K2 Horizon 7B fine-tune for documents,
spreadsheets, and tool-assisted tasks. This Q4_K_M GGUF build uses the
embedded chat template and enables reasoning by default. Applications
must provide the tools; the model download does not include workspace tools.
Repository: localaiLicense: apache-2.0
diplodocus-preview-q6
Diplodocus preview 4 is OsaurusAI's K2 Horizon 7B fine-tune for documents,
spreadsheets, and tool-assisted tasks. This Q6_K GGUF build uses the
embedded chat template and enables reasoning by default. Applications
must provide the tools; the model download does not include workspace tools.
Repository: localaiLicense: apache-2.0
diplodocus-preview-q8
Diplodocus preview 4 is OsaurusAI's K2 Horizon 7B fine-tune for documents,
spreadsheets, and tool-assisted tasks. This Q8_0 GGUF build uses the
embedded chat template and enables reasoning by default. Applications
must provide the tools; the model download does not include workspace tools.
Repository: localaiLicense: apache-2.0
atomic-minicpm-v-4.7-35b-a3b-uncensored-q4
AtomicChat's abliterated MiniCPM-V 4.7 is a 35B mixture-of-experts model
with 3B active parameters for chat and image understanding. This
AD-Q4_K-IQ4_XS build includes all 11 weight shards and the F16 vision
projector, with the embedded chat template and a 32K-token default context.
Repository: localaiLicense: apache-2.0
atomic-minicpm-v-4.7-35b-a3b-uncensored-q6
AtomicChat's abliterated MiniCPM-V 4.7 is a 35B mixture-of-experts model
with 3B active parameters for chat and image understanding. This
AD-Q6_K build includes all 16 weight shards and the F16 vision
projector, with the embedded chat template and a 32K-token default context.
Repository: localaiLicense: apache-2.0
huihui-qwen3.8-flash-next-abliterated-v2-q4
Huihui's second abliterated Qwen3.8-Flash-Next release adjusts the
abliteration without modifying the experts. This vision-language
mixture-of-experts model uses the publisher's UD-Q4_K_XL GGUF
and BF16 projector for text chat and image input through llama.cpp.
The default context is 32,768 tokens. Model weights use the
Qwen Community License 1.0.
Repository: localaiLicense: other
Page
1
of many