Q2_K_S GGUF models
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 19715 models have a Q2_K_S file. Sizes run from 2M to 671B parameters. The longest trained context is 10240K tokens.
BF
BFS Prover V1 7B i1
Bfs · mradermacher
Params7.62B
Context4K
Q4_K_M4.7 GB
TY
K2 Type 0.9B
Type · mradermacher
Params1.08B
Context128K
Q4_K_M0.7 GB
LL
Llama 4 Scout 17B 16E Instruct
Llama · mradermacher
Params108B
Context10240K
Smallest22.2 GB
QW
MathSmith HC Qwen3 14B ShortCoT
Qwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
QW
UnifiedReward 2.0 Qwen 72b
Qwen · mradermacher
Params72.7B
Context125K
Q4_K_M47.4 GB
GE
Gemma3 27B It Vl Polaris HI16 Heretic Uncensored INSTRUCT
Gemma · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
IQ
IQuest Coder V1 40B Base Stage1
Iquest · mradermacher
Params39.8B
Context16K
Q4_K_M24.0 GB
LL
Llama3.1 8b Cpt Sea Lionv3 Base
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
DE
DeepSeek R1 Distill Qwen 14B Abliterated v2
DeepSeek · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
QW
Qwen3 8B 64k Context 2X Medium
Qwen · mradermacher
Params8.19B
Context64K
Q4_K_M5.0 GB
GR
Granite 4.1 8b Heretic
Granite · mradermacher
Params8.38B
Context128K
Q4_K_M5.1 GB
LL
HARC Llama 3.1 8B Instruct
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
DE
Deepseek-Coder-V2-Lite-13B-Instruct-sft-s1K
DeepSeek · mradermacher
Params15.7B
Context160K
Q4_K_M10.4 GB
QW
Qwopus3.5 9B Coder
Qwopus · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
MI
Karen TheEditor V2 CREATIVE Mistral 7B absolute heresy i1
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
SP
Spark X2.6 1.7B Abliterated
Spark · mradermacher
Params1.71B
Context1024K
Q4_K_M1.1 GB
SA
saul zephyr 7b ties i1
Saul · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
LL
Llama Primus Nemotron 70B Instruct i1
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
QW
Qwen3 Shining Valiant Instruct Fast CODER Reasoning 2.4B
Qwen · mradermacher
Params2.43B
Context40K
Q4_K_M1.5 GB
DE
DeepSeek R1 Distill Qwen 32B Medical i1
DeepSeek · mradermacher
Params32.8B
Context128K
Q4_K_M19.9 GB
LL
PersianSciQA LLaMA 13B i1
Llama · mradermacher
Params13.3B
Context4K
Q4_K_M8.1 GB
CH
Chihiro-7B-v0.1
Chihiro · mradermacher
Params7.49B
Context32K
Q4_K_M4.5 GB
MU
TQ3.5 27B Musica v1
Musica · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
QW
Qwen2.5 Coder 14B Abliterated
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
GL
GLM 4 9B 0414
GLM · mradermacher
Params9.4B
Context32K
Q4_K_M6.2 GB
MI
MIST Mini 8B
Mist · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
RY
RynnBrain 8B
Rynnbrain · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
QW
Qwen2.5 VL 7B Instruct Unredacted MAX
Qwen · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
QW
Qwen3.6 35B A3B Abliterated v2
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
QW
AceCoder Qwen2.5 Coder 7B Ins V1.1
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB