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
Qwen3 Short Story Instruct Uncensored 262K Ctx 4B
Qwen · mradermacher
Params4.41B
Context256K
Q4_K_M2.7 GB
CodingReasoningTool use
QW
Qwen SEA LION v4 32B IT
Qwen · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
GGUF
GE
Gemma 3 4b It
Gemma · DavidAU
Params3.88B
Context128K
Q4_K_M3.3 GB
GGUF
KI
Kimi VL A3B Instruct
Kimi · mradermacher
Params16B
Context128K
Q4_K_M10.5 GB
Vision
RE
RegionReasoner 7B
Regionreasoner · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
GGUF
QW
Qwen3 0.6B
Qwen · duyntnet
Params752M
Context40K
Q4_K_M0.5 GB
ReasoningTool use
OL
OLMo 2 1124 7B
OLMo · mradermacher
Params7.3B
Context4K
Q4_K_M4.5 GB
GGUF
CO
ContaLLM Fashion 7B Instruct i1
Contallm · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
ST
Stablelm Base Alpha 7b
Stablelm · mradermacher
Params7.87B
Context4K
Q4_K_M5.1 GB
GGUF
QI
QiMing LongWriter
Qiming · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
GGUF
DE
DeepScaleR 1.5B Preview Abliterated
Deepscaler · ThomasBaruzier
Params1.78B
Context128K
Q4_K_M1.1 GB
GGUF
GE
Gemma 3 12b It Vl Polaris GLM 4.7 Flash VAR Thinking Instruct Heretic Uncensored
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
ReasoningVision
WI
Withered Calla
Withered · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
Roleplay
QW
Qwen3.5 9B GLM Wannabe
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
QW
Qwen3 ST The Next Generation II E32 v1 256k Ctx 6B
Qwen · mradermacher
Params6.33B
Context256K
Q4_K_M3.9 GB
CodingReasoning
QW
Qwen3.5 4B Element
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningRoleplayTool use
QW
Qwen3.6 27B Abliterated v1
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
SH
Shieldgemma 27b
Shieldgemma · legraphista
Params27.2B
Context8K
Smallest6.1 GB
GGUF
GE
Gemma 4 26B A4B
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
GGUF
GP
Gpt Oss 20b Heretic Scanner V1 2
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
GGUF
DE
Deepthink Reasoning 7B imatrix
Deepthink · duyntnet
Params7.62B
Context32K
Q4_K_M4.7 GB
ReasoningTool use
QW
Qwen2.5 7B OBLITERATED
Qwen · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF
DA
L3 Dark Planet 8B HERETIC Uncensored Abliterated
Dark · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
Roleplay
QW
Qwopus3.5 9B v3.5
Qwopus · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
HE
Hembot 7B v1
Hembot · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
QW
Qwen3 Coder 30B A3B Instruct 480B Distill V2 Fp32
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
Coding
MA
Magistaroth 24B v1
Magistaroth · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Tool use
OM
OmniCoder 2 9B
Omnicoder · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
ME
Mellum2.1 12B A2.5B Thinking Abliterated
Mellum · mradermacher
Params12.1B
Context128K
Q4_K_M8.1 GB
ReasoningTool use
DA
datagemma rag 27b it IMat
Datagemma · legraphista
Params27.2B
Context8K
Smallest6.1 GB
GGUF

Other quants

Keep browsing