Q3_K_S GGUF models

3-bit k-quant, small. Small files with noticeable quality loss. 102724 models have a Q3_K_S file. Sizes run from 1M to 2780B parameters. The longest trained context is 4194304K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
saraprice llama2 7B backdoor DEPLOYMENT
Llama · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
MI
Hermes-2-Pro-Mistral-7B
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
QW
Qwen3.8 27B OBLITERATED Mythos Class Agentic
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
GP
Gpt Oss 20b Unsloth Puzzle V2
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
Reasoning
TR
TranslatePsy AfriSLM 4B
Translatepsy · mradermacher
Params4.84B
Context256K
Q4_K_M3.1 GB
ReasoningTool use
MI
lemonilia_ashhlimarp-mistral-7b
Mistral · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ON
OneJev 0.8B
Onejev · bartowski
Params1.01B
Context256K
Q4_K_M0.7 GB
Vision
LL
Llama Leonida
Llama · mradermacher
Params8.2B
Context128K
Q4_K_M5.0 GB
Tool use
AI
aixsatoshi Ex karakuri 8x12B chat v1
Aixsatoshi · mmnga
Params81.5B
Context32K
Smallest17.1 GB
GGUF
LL
models--mergekit-community--Llama3-13B-ku
Llama · MaziyarPanahi
Params23B
Context8K
Q4_K_M13.9 GB
Tool use
ME
models--automerger--T3qm7Mergerix-7B
Mergerix · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
NE
Nethena-20B
Nethena · mradermacher
Params20B
Context4K
Q4_K_M12.0 GB
GGUF
LL
llama 2 13B chat limarp v2 merged
Llama · TheBloke
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
AN
Andromeda 8B Coder i1
Andromeda · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
CodingTool use
YA
models--automerger--Experiment28Yam-7B
Yam · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ST
stablelm zephyr 3b
Stablelm · TheBloke
Params2.8B
Context4K
Q4_K_M1.7 GB
GGUF
EV
EAN 7B i1
Evan · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Reasoning
QW
OpenBuddy OpenBuddy R1 0528 Distill Qwen3 32B Preview0 QAT
Qwen · bartowski
Params32.8B
Context40K
Q4_K_M19.8 GB
Reasoning
SU
SummLlama3 8B i1
Summllama · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Trohrbaugh Qwen3.5 122B A10B Heretic
Qwen · mradermacher
Params122B
Context256K
Q4_K_M74.2 GB
ReasoningTool use
QW
Qwen3-4B-128K
Qwen · unsloth
Params4B
Context128K
Q4_K_M2.5 GB
GGUF
QW
Qwen3.5 35B RpRMax v1
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
TI
Tiamat-7b-1.1-DPO
Tiamat · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
Llama-3-Patronus-Lynx-8B-Instruct
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
RO
ROMA 7B
Roma · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
GE
Gemma 4 31B It Mystery Fine Tune HERETIC UNCENSORED Thinking
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
CodingReasoningRoleplay
LL
meta-llama-7b
Llama · TheBloke
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
GR
GRM 2.6 Plus 0628
Grm · bartowski
Params27.3B
Context256K
Q4_K_M17.8 GB
Vision
SW
Swallow-70b-instruct-v0.1
Swallow · mradermacher
Params69.2B
Context4K
Q4_K_M41.5 GB
GGUF
KA
KAI 7B v0.1
Kai · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Coding

Other quants

Keep browsing