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
OB
oblivionsend i1
Oblivionsend · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
QW
Qwen3.8 27B ASCII Condensed
Qwen · troed
Params1.86B
Context256K
Smallest0.5 GB
GGUF
MI
Mistral Nemo 2407 Instruct 12B Deep Thinking Claude Gemini GPT5.2
Mistral · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
ReasoningRoleplay
GE
Gemma 4 12b Crownelius Writer
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
GGUF
OC
Occamy 1.0
Occamy · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
Tool use
ME
Mellum2 12B A2.5B Instruct
Mellum · mradermacher
Params12.1B
Context128K
Q4_K_M8.1 GB
Tool use
HE
Hemlock Coder 7B
Hemlock · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
WI
WizardLM-13B-Uncensored
Wizardlm · duyntnet
Params13B
Context2K
Q4_K_M7.9 GB
GGUF
GE
Gemma 4 31B Isometry RP
Gemma · mradermacher
Params32.1B
Context256K
Q4_K_M19.5 GB
Roleplay
QW
Qwen3-8B-grpo-medmcqa-v2
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
Reasoning
QW
Omega Qwen3 Atom 8B
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
CodingReasoning
AU
Aurora SCE 12B i1
Aurora · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
RY
RynnBrain Plan 8B
Rynnbrain · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
CodingTool useVision
DE
DeepSeek Coder V2 Instruct 0724
DeepSeek · legraphista
Params236B
Context160K
Smallest47.4 GB
CodingTool use
QW
SmartSnap Qwen2.5 7B
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
GL
GLM 4.5 DRAFT 0.6B v3.0
GLM · mradermacher
Params629M
Context32K
Q4_K_M0.5 GB
GGUF
QW
Qwen3 VisionCaption 2B It REDACTED
Qwen · mradermacher
Params1.72B
Context256K
Q4_K_M1.1 GB
Tool useVision
QW
Qwen3.6 27B Abliterated v2
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
HA
Harbinger 24B
Harbinger · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
MI
Mistral Devstral 2507 CODER Brainstorm40x 44B
Mistral · mradermacher
Params43.6B
Context128K
Q4_K_M26.4 GB
CodingTool use
ZE
Zen Pro
Zen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
CY
Cypher CoT 1.8B i1
Cypher · mradermacher
Params1.83B
Context16K
Q4_K_M1.1 GB
Coding
GE
Gemma 4 26B A4B It Claude Opus Distill v2
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
LL
Llama 2 7b chat norwegian i1
Llama · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
MI
WEBGEN Devstral 24B
Mistral · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
CodingTool use
SP
spider skeleton wizard coder merged i1
Spider · mradermacher
Params15.5B
Context8K
Q4_K_M10.0 GB
Coding
MI
Mistral Small 24B Instruct 2501
Mistral · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
Reasoning
FA
Famino 12B Model_Stock
Famino · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
QW
Qwen3 30B A3B Element6 1M
Qwen · mradermacher
Params30.5B
Context1024K
Q4_K_M18.6 GB
ReasoningRoleplay
FA
Falcon H1 3B Instruct
Falcon · tiiuae
Params3.15B
Context128K
Q4_K_M1.9 GB
GGUF

Other quants

Keep browsing