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.

Most downloadedNewestLargestLongest contextSmallest
QW
Heretic Qwen3 VL 235B A22B Instruct i1
Qwen · mradermacher
Params235B
Context—
Smallest0.5 GB
GGUF
QW
Qwen3.5 21B GLM 4.7 Flash Heretic Uncensored Thinking
Qwen · mradermacher
Params20.8B
Context256K
Q4_K_M12.9 GB
CodingReasoningRoleplay
QW
Qwen2.5 0.5B Instruct Abliterated
Qwen · mradermacher
Params494M
Context32K
Q4_K_M0.4 GB
Tool use
IN
InfinityKuno 2x7B i1
Infinitykuno · mradermacher
Params12.9B
Context32K
Q4_K_M7.8 GB
GGUF
OR
Ornith 1.5 35B A3B Abliterated
Ornith · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
QW
Suri Qwen 3.5 9B Uncensored Soft
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
QW
ZYH LLM Qwen2.5 14B V3 i1
Qwen · mradermacher
Params14.8B
Context986K
Q4_K_M9.0 GB
Tool use
PH
Phr00tyMix v4 32B
Phr · mradermacher
Params32.8B
Context128K
Q4_K_M19.8 GB
GGUF
GP
gpt oss 6.0b specialized all pruned moe only 7 experts i1
gpt-oss · mradermacher
Params5.98B
Context128K
Q4_K_M4.6 GB
ReasoningTool use
AI
Airoboros 65b Gpt4 1.4
Airoboros · mradermacher
Params65.3B
Context2K
Q4_K_M39.3 GB
GGUF
ST
Starlight Synthesis 31B
Starlight · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
Roleplay
GL
Gliese OCR 7B Post2.0 Final
Gliese · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
LL
Llama 3.1 Swallow 8B Instruct v0.5
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
DA
Dark World 24B v1
Dark · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
AN
Anime Llasa 3B
Anime · mradermacher
Params3.41B
Context128K
Q4_K_M2.2 GB
Tool use
LL
Llama TI 8B i1
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
CodingReasoning
DE
FuseO1 DeepSeekR1 Qwen2.5 Coder 32B Preview
DeepSeek · mradermacher
Params32.8B
Context128K
Q4_K_M19.9 GB
CodingTool use
OL
AMD OLMo 1B IT
OLMo · mradermacher
Params1.18B
Context2K
Q4_K_M0.7 GB
GGUF
QW
Qwen3 VL 8B Instruct Uncensored V2
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool useVision
QW
Qwen3 VL 8B Instruct Uncensored
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool useVision
LL
LLaDA MoE 7B A1B Instruct
Llada · mradermacher
Params7.36B
Context8K
Q4_K_M4.5 GB
ReasoningTool use
GP
Gpt Oss 120b Guardpoint
gpt-oss · mradermacher
Params117B
Context128K
Q4_K_M87.9 GB
Reasoning
QW
Qwen3.5 9B
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
NI
NinjaMouse 3B 40L Danube
Ninjamouse · mradermacher
Params2.94B
Context16K
Q4_K_M1.8 GB
Coding
LU
Luminous Shadow 12B
Luminous · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
CO
ConspLLM 7b
Conspllm · mradermacher
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
QW
Qwen3.5 13B Star Trek TNG DS9 Heretic Uncensored Thinking
Qwen · mradermacher
Params12.4B
Context256K
Q4_K_M7.7 GB
ReasoningRoleplayTool use
SK
sky t1 coder 32b flash i1
Sky · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
CodingTool use
ME
meditron-7b
Meditron · duyntnet
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
LL
Reflection Llama 3.1 70B IMat
Llama · legraphista
Params70.6B
Context8K
Smallest15.3 GB
GGUF

Other quants

Keep browsing