GGUF models by win10

97 GGUF models quantized by win10 on Hugging Face. Sizes run from 21M to 40.6B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
DE
DeepSeek-Coder-V2-Lite-Instruct
DeepSeek · win10
Params15.7B
Context160K
Smallest14.1 GB
Coding
DE
DeepSeek-Coder-V2-Lite-Instruct
DeepSeek · win10
Params15.7B
Context160K
Smallest16.7 GB
Coding
LL
Llama 3.2 3B Instruct 24 9 29
Llama · win10
Params3.21B
Context128K
Smallest3.4 GB
Tool use
BR
Breeze 7B FC v1 0 EvolKit 75K Nopm_Claude_Writing_Fixed Adapter
Breeze · win10
Params21M
Context—
Smallest0.1 GB
GGUF
GP
GPT OSS 26B Abliterated Preview
gpt-oss · win10
Params25.9B
Context128K
Smallest27.5 GB
GGUF
MI
Mistral Nemo Instruct 2407
Mistral · win10
Params22.6B
Context1000K
Smallest24.0 GB
Tool use
MI
Mistral Nemo abliterated Nemo Pro v2 Q8 0
Mistral · win10
Params12.2B
Context1000K
Smallest13.0 GB
Tool use
NA
K2 Nano
Nano · win10
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningTool useVision
GP
GPT OSS 26B Abliterated Preview
gpt-oss · win10
Params25.9B
Context128K
Q4_K_M19.4 GB
GGUF
MI
Mistral Nemo Instruct 2407
Mistral · win10
Params22.6B
Context1000K
Q4_K_M13.7 GB
Tool use
LU
Lusca 33B Q4 K M
Lusca · win10
Params33.2B
Context128K
Q4_K_M19.9 GB
GGUF
PH
phi 3.5 Sakura Yuzu v1.5 Q8 0
Phi · win10
Params3.82B
Context4K
Smallest4.1 GB
GGUF
CH
ChatML Nemo Pro
Chatml · win10
Params12.2B
Context1000K
Smallest13.0 GB
GGUF
QW
Qwen2.5 Coder 12.3b Instruct Q8 0
Qwen · win10
Params12.3B
Context32K
Smallest13.1 GB
CodingTool use
QW
Qwen3.8 27b EXP EVE
Qwen · win10
Params27.3B
Context256K
Smallest29.0 GB
GGUF
SP
SphinxMind 14B normalize false Q8 0
Sphinxmind · win10
Params14.8B
Context64K
Smallest15.7 GB
GGUF
QW
Norns Qwen2.5 12B Q8 0
Qwen · win10
Params12.3B
Context32K
Smallest13.1 GB
GGUF
IN
Internlm2_5 20b Chat Abliterated
InternLM · win10
Params19.9B
Context32K
Smallest16.3 GB
GGUF
LI
Lingshu 32B
Lingshu · win10
Params32.8B
Context125K
Q4_K_M19.9 GB
ReasoningVision
MI
Miscii 14b 1028
Miscii · win10
Params14.8B
Context128K
Smallest15.7 GB
RoleplayTool use
EV
EVA Meissa mini pro Q8 0
Eva · win10
Params14.8B
Context64K
Smallest15.7 GB
GGUF
MA
MagiDevs 24B 2506 Vision
Magidevs · win10
Params23.6B
Context128K
Smallest25.1 GB
Vision
QW
EVA Norns Qwen2.5 v0.1 Q8 0
Qwen · win10
Params7.62B
Context128K
Smallest8.1 GB
GGUF
LL
llama3-13.45b-Instruct
Llama · win10
Params13.3B
Context8K
Smallest10.9 GB
GGUF
PI
Pixtral 12B 2409 Hf Text Only
Pixtral · win10
Params12.2B
Context1000K
Smallest13.0 GB
Tool useVision
MA
Magnum v2 12b
Magnum · win10
Params12.2B
Context1000K
Smallest13.0 GB
GGUF
DE
DeepSeek R1 Distill sthenno 14b 0121 Q8 0
DeepSeek · win10
Params14.8B
Context128K
Smallest15.7 GB
Reasoning
PH
phi3.5 pro 10 08 Q8 0
Phi · win10
Params4.95B
Context128K
Smallest5.3 GB
GGUF
KW
KwaiCoder AutoThink Preview
Kwaicoder · win10
Params40.6B
Context32K
Q4_K_M24.6 GB
CodingTool use
MA
MagiDevs 24B 2506 Vision
Magidevs · win10
Params23.6B
Context128K
Smallest19.3 GB
Vision

About win10 on Hugging Face

win10 has published 97 GGUF models that ggufmodels.com tracks, across families such as Qwen, Phi and Mistral. The most downloaded are DeepSeek-Coder-V2-Lite-Instruct, DeepSeek-Coder-V2-Lite-Instruct and Llama 3.2 3B Instruct 24 9 29.

The quants win10 publishes most often are Q8_0 (64), Q4_K_M (18), Q6_K (11) and Q5_K_M (5). Their Q4_K_M files range from 7.5 to 24.6 GB. Parameter counts run from 21M to 40.6B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has win10 published?

97 models are listed here, mainly from the Qwen, Phi and Mistral families. The most downloaded is DeepSeek-Coder-V2-Lite-Instruct.

Which quants does win10 publish?

The most common are Q8_0 (64 models), Q4_K_M (18 models), Q6_K (11 models) and Q5_K_M (5 models).

Keep browsing