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
GL
Huihui GLM 4.7 Flash Abliterated 60B_DEPTHONLY
GLM · mradermacher
Params59.2B
Context198K
Q4_K_M35.8 GB
GGUF
QW
Sanskrit Qwen 7B Translate v2
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
GE
Gemma 3 27b It Vl SuperBrain7x High Reasoning ULTRAMIND Heretic Uncensored
Gemma · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
ReasoningVision
QW
Gemini 3 Pro Qwen3.5 35B A3B
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
GL
GLM 4.7 Flash REAP 19
GLM · mradermacher
Params24.7B
Context198K
Q4_K_M15.0 GB
CodingReasoningTool use
AI
Airoboros L2 7b 3.0
Airoboros · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
QW
Qwen3 VL 4B Instruct Uncensored
Qwen · mradermacher
Params4.02B
Context256K
Q4_K_M2.5 GB
Tool useVision
GE
Geneva 12B GCv2 50k
Geneva · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
FL
Fluxnat Coder 3B
Fluxnat · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
Coding
MA
UI Mate 9B Heretic
Mate · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
DA
Darwin 9B NEG
Darwin · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
QW
Qwen3 16B QiMing V1.0 Total Recall Light
Qwen · mradermacher
Params16.1B
Context40K
Q4_K_M9.8 GB
CodingReasoningTool use
QW
Qwen3.6 35B A3B Opus Reasoning
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
OL
OLMo 2 1124 13B DPO Preview
OLMo · mradermacher
Params13.7B
Context4K
Q4_K_M8.4 GB
GGUF
PO
Poppy Porpoise v0.7 L3 8B i1
Poppy · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GE
Gemma 3 4b It Claude
Gemma · mradermacher
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
MI
Mistral 7B Instruct v0.2 Abliterated Obliteratus
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
SmartSnap Qwen3 32B
Qwen · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
ReasoningTool use
GP
Gpt Oss 20b Person v1
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
Tool use
HE
Hemlock Tincture 14B
Hemlock · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
Tool use
ER
ERNIE 4.5 HUGE 51B A3B Thinking Brainstorm40x
Ernie · mradermacher
Params50.7B
Context128K
Q4_K_M30.7 GB
CodingReasoningTool use
QW
Omega Qwen2.5 Coder 3B
Qwen · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
CodingReasoningTool use
IN
InternVL3 78B Pretrained
Internvl · mradermacher
Params72.7B
Context32K
Q4_K_M47.4 GB
CodingTool use
KE
KernelGen LM 32B
Kernelgen · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
CodingReasoningTool use
QW
Qwen2.5 32B Instruct Abliterated v2
Qwen · BasedAGI
Params32.8B
Context32K
Q4_K_M19.9 GB
GGUF
MI
Heidrun Mistral 7B chat i1
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
LL
Llama 4 Scout 17B 16E Instruct Abliterated v2
Llama · mradermacher
Params108B
Context10240K
Smallest22.2 GB
GGUF
OR
Orion 14B Base
Orion · mradermacher
Params14.5B
Context4K
Q4_K_M8.8 GB
Coding
OR
Ornith1.5 9B 3MPER0RR Abliterated
Ornith · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
HU
Huihui MoE 60B A3B Abliterated
Huihui · mradermacher
Params59.5B
Context256K
Q4_K_M36.2 GB
ReasoningTool use

Other quants

Keep browsing