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
CR
CrucibleLab L3.3 70B Loki V2.0 Heretic Uncensored
Cruciblelab · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
RoleplayTool use
LL
OpenMath CodeLlama 7b Python Hf
Llama · mradermacher
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
DE
Deepseek Coder 33b Secure
DeepSeek · mradermacher
Params33.3B
Context16K
Q4_K_M19.9 GB
Coding
LO
LOGOS 8B
Logos · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
LL
Llama 3.1 8B Instruct Uncensored Complete
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
AT
Atomight V2.5 1.7B C1
Atomight · mradermacher
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
QW
Huihui Qwen3.5 9B Abliterated Grimoire KTO
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
QW
Qwen3.6 35B A3B Claude 4.6 Opus Reasoning Distilled
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
QW
Qwen3 Jan Nano 128k 6B Brainstorm20x
Qwen · mradermacher
Params5.94B
Context128K
Q4_K_M3.6 GB
CodingReasoningTool use
MO
G4 Moonlight Dusk 26B A4B
Moonlight · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
Roleplay
SA
SADeepCoder 14B Preview Unsloth v1.0
Sai · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
CodingReasoningTool use
DA
Darwin 35B A3B Opus
Darwin · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
RO
Rocinante XL 16B v1 Desiccated
Rocinante · mradermacher
Params16.1B
Context128K
Q4_K_M9.7 GB
Tool use
GE
Gemma 4 26B A4B It Multitool
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
QW
Qwen2.5 Microsoft NextCoder Brainstorm20x 128k Ctx 12B
Qwen · mradermacher
Params12B
Context128K
Q4_K_M7.3 GB
CodingTool use
LL
Llama2 MedTuned 13b
Llama · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
GE
Gemma 4 12B It Blorbo V0B
Gemma · mradermacher
Params12.9B
Context256K
Q4_K_M7.9 GB
ReasoningRoleplayTool use
HU
Huihui Qwopus3.5 4B v3 Abliterated
Huihui · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
Reasoning
OP
OpenBuddy R10528DistillQwen 14B v27.3 200K
Openbuddy · mradermacher
Params14.8B
Context195K
Q4_K_M9.0 GB
GGUF
GR
Granite 4.2 8b
Granite · mradermacher
Params8.79B
Context128K
Q4_K_M5.3 GB
ReasoningTool use
KA
Katarau 9B Ru RP Nsfw
Katarau · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Roleplay
GR
IBM Granite 4.1 8b Heretic
Granite · mradermacher
Params8.38B
Context128K
Q4_K_M5.1 GB
GGUF
VI
VibeThinker 1.5B
Vibethinker · prithivMLmods
Params1.78B
Context128K
Q4_K_M1.1 GB
Coding
LL
pub llama 13B v5 i1
Llama · mradermacher
Params13.2B
Context2K
Q4_K_M8.0 GB
GGUF
NE
Nemotron Terminal 14B Heretic
Nemotron · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
CodingReasoningTool use
QW
Qwen2.5-Omni-3B
Qwen · Mungert
Params3.4B
Context32K
Q4_K_M2.2 GB
GGUF
KE
Kepler Reasoning 7B
Kepler · mradermacher
Params7.61B
Context32K
Q4_K_M4.7 GB
CodingReasoningTool use
FR
Froopert 31B
Froopert · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningRoleplayTool use
GP
Gpt Oss Safeguard 20b
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
Tool use
NI
Nizam LLM 7B
Nizam · mradermacher
Params7B
Context4K
Q4_K_M4.3 GB
GGUF

Other quants

Keep browsing