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.
QW
Qwen3 ST The Next Generation II v1 256k Ctx 6B
Qwen · mradermacher
Params6.33B
Context256K
Q4_K_M3.9 GB
BI
BiMediX2 8B Hf
Bimedix · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
HE
HERETICODER 2.5 7B IT
Hereticoder · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
LL
Llama 3 JPRP NSFW 8B
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GE
Gemma 3 1B It GLM 4.7 Flash Heretic Uncensored Thinking
Gemma · mradermacher
Params1B
Context32K
Q4_K_M0.8 GB
PH
Phi 3 medium 128k instruct imatrix
Phi · hermes42
Params14B
Context128K
Q4_K_M8.6 GB
QW
GeoLLM Qwen3.5 27B
Qwen · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
QW
Qwen2.5 32B Instruct Darija
Qwen · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
QW
OneThinker SFT Qwen3 8B
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
AZ
Aztec Coder 4B
Aztec · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
CA
CantoneseLLM v2.0 30B A3B Thinking
Cantonesellm · mradermacher
Params30.5B
Context40K
Q4_K_M18.6 GB
YI
Yi-6B-Chat
Yi · mradermacher
Params6.06B
Context4K
Q4_K_M3.7 GB
QW
shisa v2.1 qwen3 8b i1
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
LL
Llama3.2 3B Math Gsm8K AutoSFT
Llama · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
GE
Gemma 4 AssGuard 31B
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
OL
OLMoE 1B 7B 0125 i1
OLMo · mradermacher
Params6.9B
Context4K
Q4_K_M4.2 GB
UW
UwU 14B Math v0.2 i1
Uwu · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
OM
Omni R1 Zero
Omni · mradermacher
Params7.01B
Context10K
Q4_K_M4.3 GB
MI
Huihui Ministral 3 3B Reasoning 2512 Abliterated
Mistral · mradermacher
Params3.43B
Context256K
Q4_K_M2.1 GB
LL
Arabic llama3 i1
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GR
Granite Guardian 3.3 8b
Granite · mradermacher
Params8.17B
Context128K
Q4_K_M4.9 GB
GE
Gemma 4 26B A4B It Heretic Antislop
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
QW
Qwopus3.5 9B v3
Qwopus · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
FA
gpt4all falcon i1
Falcon · mradermacher
Params7.22B
Context2K
Q4_K_M5.0 GB
ZH
Zhi Create DSR1 14B
Zhi · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
SH
Shisa K 12B
Shisa · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
QI
QiMing Janus
Qiming · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
SW
SWE Review 8B
Swe · mradermacher
Params8.19B
Context160K
Q4_K_M5.0 GB
MA
Magidonia 24B v4.3 Heretic v4
Magidonia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
DE
Delexa-Instruct-V0.1-7b
Delexa · duyntnet
Params7.24B
Context32K
Q4_K_M4.4 GB