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
NE
NextCoder Mirage Sol 7B
Nextcoder · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
QW
Qwen2.5 QwQ 37B Eureka Triple Cubed i1
Qwen · mradermacher
Params36.7B
Context128K
Q4_K_M22.2 GB
ReasoningTool use
AU
Aura 4B
Aura · mradermacher
Params4.51B
Context128K
Q4_K_M2.8 GB
RoleplayTool use
CA
Calme-7B-Instruct-v0.4
Calme · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
GP
Gpt Oss 20b Coding Distill
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
CodingReasoningTool use
MA
Marco DeepResearch 8B
Marco · ATH-MaaS
Params8.19B
Context128K
Q4_K_M5.0 GB
ReasoningTool use
QW
Qwen3 Nemotron 32B RLBFF
Qwen · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
ReasoningTool use
FA
Falcon H1 34B Base
Falcon · mradermacher
Params33.6B
Context256K
Q4_K_M20.3 GB
GGUF
GO
Golden Curry 12B
Golden · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
TO
TowerInstruct 13B v0.1 EN2ES
Towerinstruct · mradermacher
Params13B
Context8K
Q4_K_M7.9 GB
GGUF
LL
Llama Gujarat 8B
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
GE
Gemma 3 12b It
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
QW
Huihui Qwen3 VL 30B A3B Thinking Abliterated
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
ReasoningTool useVision
LL
Llama 3 3 Nemotron Super 49B v1 5 i1
Llama · mradermacher
Params49.9B
Context128K
Q4_K_M30.2 GB
ReasoningTool use
QW
Qwen3.5 27B_Homebrew
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
QW
WhereOPD Qwen3.5 9B
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
VY
VyvoTTS LFM2 350M Jenny
Vyvotts · mradermacher
Params383M
Context125K
Q4_K_M0.3 GB
Tool use
FI
v6 Finch 3B HF
Finch · mradermacher
Params3.1B
Context1024K
Q4_K_M1.9 GB
GGUF
OU
13B Ouroboros
Ouroboros · mradermacher
Params13B
Context2K
Q4_K_M7.9 GB
GGUF
QW
Qwen3 MOE 2x4B 8B Jan Nano Instruct II
Qwen · mradermacher
Params6.71B
Context40K
Q4_K_M4.1 GB
CodingReasoningTool use
QW
Qwen3 Code Reasoning Instruct 6B Brainstorm20x
Qwen · mradermacher
Params5.94B
Context40K
Q4_K_M3.6 GB
CodingReasoningTool use
GR
Granite 3.3 2b Instruct Heretic Safety Defiltered
Granite · mradermacher
Params2.53B
Context128K
Q4_K_M1.5 GB
GGUF
FA
Falcon H1 7B Base
Falcon · mradermacher
Params7.59B
Context256K
Q4_K_M4.6 GB
GGUF
PR
PromptEnhancer Img2img Edit
Promptenhancer · mradermacher
Params32.8B
Context125K
Q4_K_M19.9 GB
GGUF
MI
Ministral Instruct 2410 8B DPO RP i1
Mistral · mradermacher
Params8.02B
Context32K
Q4_K_M4.9 GB
RoleplayTool use
LL
Hermes 3 Llama 3.2 3B
Llama · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
RoleplayTool use
QW
Josiefied Qwen2.5 Coder 7B Instruct abliterated v1 i1
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
QW
Qwen3.6 27B
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
UN
UNA-TheBeagle-7b-v1
Una · duyntnet
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
HO
Hormoz
Hormoz · mradermacher
Params8.03B
Context8K
Q4_K_M5.1 GB
GGUF

Other quants

Keep browsing