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.
DE
DeepSeek V2 Lite Chat Uncensored
DeepSeek · mradermacher
Params15.7B
Context160K
Q4_K_M10.4 GB
KA
Kaidol Thinking Sft 4b
Kaidol · mradermacher
Params4.41B
Context256K
Q4_K_M2.7 GB
LL
SenecaLLM x Llama3.1 8B i1
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GE
GEITje 7B
Geitje · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
BI
Bielik PL 11B v3.0 Instruct Ungated
Bielik · mradermacher
Params11.2B
Context32K
Q4_K_M6.7 GB
QW
Qwen2.5 Coder 7B Instruct OBLITERATED
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
QW
Qwen3.5 9B Base
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GE
DarkIdol Gemma 4 31B It
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
LL
Llama 3.1 Taiwan 8B
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
HP
hpc coder v2 16b i1
Hpc · mradermacher
Params15.7B
Context160K
Q4_K_M10.4 GB
QW
MathSmith Qwen3 8B LongCoT
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
QW
Qwen3 Zero Coder Reasoning Brainstorm5x 0.9B
Qwen · mradermacher
Params879M
Context40K
Q4_K_M0.6 GB
CO
Cosmos 8B Instruct SFT
Cosmos · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
QW
Qwen2.5 1.5B Instruct
Qwen · duyntnet
Params1.54B
Context32K
Q4_K_M1.0 GB
LL
Lawyer Llama 13b v2
Llama · mradermacher
Params13.3B
Context4K
Q4_K_M8.1 GB
QW
Huihui Qwen3.5 2B Abliterated
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
GE
Gemma 3 Glitter 12B
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
EG
EgoThinker v1
Egothinker · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
FO
Forsaken Void 12B
Forsaken · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
NE
Nexus Flash 9B
Nexus · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ME
Medra4b Abliterated
Medra · Guilherme34
Params4.55B
Context128K
Q4_K_M2.9 GB
QW
Qwen3 14B Cobalt2
Qwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
RO
RoLlama2-7b-Chat
Rollama · legraphista
Params6.74B
Context4K
Smallest1.5 GB
OP
OpenCodeInterpreter-DS-6.7B
Opencodeinterpreter · duyntnet
Params6.74B
Context16K
Q4_K_M4.1 GB
HE
Hemlock Apothecary 7B GRPO E3
Hemlock · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
SP
Spaetzle v60 7b i1
Spaetzle · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
TR
Trinity Mini Base Pre Anneal
Trinity · mradermacher
Params26B
Context4K
Q4_K_M15.8 GB
QW
Josiefied Qwen2.5 14B Instruct Abliterated v4
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
KI
Kimi Linear 48B A3B Base
Kimi · mradermacher
Params49.1B
Context1024K
Q4_K_M29.7 GB
LL
Llama 3.2 3B Instruct
Llama · ThomasBaruzier
Params3.21B
Context128K
Q4_K_M2.0 GB