Model Gallery
Discover and install AI models from our curated collection
Find Your Perfect Model
Filter by Model Type
Browse by Tags
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-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
qwen3.5-4b-3d-coder-q8
CCORE's early preview fine-tune of Qwen3.5-4B for coding and Three.js
scene generation. This text-only Q8_0 build pins a preview
checkpoint and uses the embedded chat template. MTP is not enabled.
Repository: localaiLicense: apache-2.0
sage-a1.5-q4
Sage-A1.5 is a 35B mixture-of-experts model based on Qwen3.6 for
scientific reasoning, coding, and tool use. This official Q4_K_M GGUF
build uses llama.cpp and includes the vision projector.
Repository: localaiLicense: apache-2.0
sage-a1.5-q8
Sage-A1.5 is a 35B mixture-of-experts model based on Qwen3.6 for
scientific reasoning, coding, and tool use. This official Q8_0 GGUF
build uses llama.cpp and includes the vision projector.
Repository: localaiLicense: apache-2.0
tess-4.5-27b-q4
Tess 4.5 is a 27B Qwen3.8 fine-tune for coding, reasoning, and tool use.
This Q4_K_M GGUF build includes the F16 vision projector and uses
llama.cpp with the embedded chat template. Speculative decoding is disabled.
Repository: localaiLicense: apache-2.0
tess-4.5-27b-q6
Tess 4.5 is a 27B Qwen3.8 fine-tune for coding, reasoning, and tool use.
This Q6_K GGUF build includes the F16 vision projector and uses
llama.cpp with the embedded chat template. Speculative decoding is disabled.
Repository: localaiLicense: apache-2.0
tess-4.5-27b-q8
Tess 4.5 is a 27B Qwen3.8 fine-tune for coding, reasoning, and tool use.
This Q8_0 GGUF build includes the F16 vision projector and uses
llama.cpp with the embedded chat template. Speculative decoding is disabled.
Repository: localaiLicense: apache-2.0
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
deepseek-v4.1-flash-1017
# DeepSeek-V4.1-Flash-1017
Technical Report 👁️
## Introduction
**DeepSeek-V4.1-Flash-1017** is a minor update to **DeepSeek-V4.1-Flash**, delivering substantial improvements across reasoning, coding, agentic tasks, and visual benchmarks. Alongside these gains, the model reduces task execution time and output length, enabling users to complete tasks faster and at lower cost and advancing the performance–cost Pareto frontier across multiple agent harnesses.
*† denotes the text-only subset of HLE. We use the Claude Code harness for Terminal-Bench 4.0 and the Mini-SWE-V2 harness for DeepSWE v1.1.*
## Prompt Encoding
This release does not include a Jinja-format chat template. The `encoding` folder contains a self-contained Python reference implementation (`encoding.py`) with test cases for multi-turn conversations, tool calling, thinking mode, numeric reasoning effort, mid-conversation system messages, and interleaved image content.
...
Repository: localaiLicense: mit
qwen3.8-27b-imatrix-nvfp4-mtp
Qwen3.8-27B in cdiamond's iMatrix-calibrated mixed-precision NVFP4
build. Selected attention and feed-forward tensors retain higher
precision. Includes the F16 vision projector and enables the embedded
MTP draft head with one draft token per step.
Repository: localaiLicense: apache-2.0
underdog-saluki-27b-1.0-abliterated
Kujira's abliterated adaptation of Underdog Saluki 27B 1.0 uses mixed
IQ2 weights with an embedded MTP head. This text-only llama.cpp build
uses ordinary decoding; the MTP variant enables speculative decoding.
Repository: localaiLicense: apache-2.0
glm-5.3-flash-maya-s
GLM-5.3-Flash is a mixture-of-experts model for reasoning, coding, tool use, and vision. Maya-S v2 mixes IQ2_XXS and IQ2_S experts with Q6_K attention and shared experts.
Repository: localaiLicense: mit
glm-5.3-flash-maya-s24
GLM-5.3-Flash is a mixture-of-experts model for reasoning, coding, tool use, and vision. Maya-S24 uses mixed 2-bit experts with Q4_K attention and shared experts.
Repository: localaiLicense: mit
glm-5.3-flash-maya-m
GLM-5.3-Flash is a mixture-of-experts model for reasoning, coding, tool use, and vision. Maya-M uses mixed 2-bit and 3-bit experts with Q6_K attention and shared experts.
Repository: localaiLicense: mit
glm-5.3-flash-maya-l
GLM-5.3-Flash is a mixture-of-experts model for reasoning, coding, tool use, and vision. Maya-L uses mixed 3-bit and 4-bit experts with higher precision in sensitive layers.
Repository: localaiLicense: mit
Page
1
of many