Q3_K_M GGUF models

3-bit k-quant, medium. Small files with some quality loss. 108680 models have a Q3_K_M file. Sizes run from 1M to 2780B parameters. The longest trained context is 4194304K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
qwen image
Qwen · calcuis
Params20.4B
Context—
Q4_K_M11.7 GB
GGUF
LL
LogDoctor Llama 3.1 8B
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Tool use
DI
discoresearch_discolm_german_7b_v1
Discolm · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
CL
Clef Artemis
Clef · turintech
Params27B
Context256K
Smallest10.5 GB
ReasoningTool use
OR
Ornith 1.5 122B DFlash2
Ornith · kaivoss
Params930M
Context256K
Q4_K_M0.6 GB
GGUF
ST
G4 Starry Ocean 12B Heretic
Starry · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
ReasoningRoleplayTool use
QW
Qwen3.5 27B Writer V2 Uncensored Heretic
Qwen · llmfan46
Params27B
Context256K
Q4_K_M16.5 GB
Vision
QW
Qwen Image 2512
Qwen · byteshape
Params20.4B
Context—
Q4_K_M11.4 GB
GGUF
MI
Minimax-M2.1
Minimax · unsloth
Params230B
Context192K
Q4_K_M138.3 GB
GGUF
IN
InternVL3_5 14B
Internvl · bartowski
Params14.8B
Context40K
Q4_K_M9.0 GB
Vision
SA
SauerkrautLM 7b LaserChat
Sauerkrautlm · mradermacher
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
CY
Cydonia 24B v4.3 Heretic v4
Cydonia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Coding
CO
Cosmos-Reason1-7B
Cosmos · unsloth
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
QW
Qwen3 Vl 4b Heretic
Qwen · DreamFast
Params4B
Context256K
Q4_K_M2.5 GB
Vision
LL
phind_phind-codellama-34b-python-v1
Llama · TheBloke
Params33.7B
Context16K
Q4_K_M20.2 GB
Coding
GE
Gemma 3 4b It Qat
Gemma · bartowski
Params3.88B
Context128K
Q4_K_M2.5 GB
Vision
LI
LightOnOCR 3 0.8B
Lightonocr · Prathat
Params752M
Context256K
Q4_K_M0.5 GB
Vision
DE
DeepSeek R1 Distill Qwen 7B Abliterated v2
DeepSeek · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
Reasoning
QW
Qwen3.8 27B
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
GGUF
LL
Llama 3.2 1B Instruct
Llama · DavidAU
Params1.24B
Context128K
Q4_K_M0.8 GB
Roleplay
OR
Orca 2 13b
Orca · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
CH
ChemLLM 20B Chat SFT i1
Chemllm · mradermacher
Params19.9B
Context32K
Q4_K_M12.0 GB
GGUF
TU
Tulu 2 7B Helpful
Tulu · mradermacher
Params6.74B
Context8K
Q4_K_M4.1 GB
GGUF
QW
Huihui ai.Qwen3 8B Abliterated
Qwen · DevQuasar
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
LI
LightOnOCR 3 0.8B
Lightonocr · prithivMLmods
Params752M
Context256K
Q4_K_M0.5 GB
Vision
PH
dolphin 2 6 phi 2
Phi · TheBloke
Params2.78B
Context2K
Q4_K_M1.8 GB
CodingTool use
LL
CodeLlama 70B Python
Llama · TheBloke
Params69B
Context4K
Q4_K_M41.4 GB
Coding
WA
Wan2.1 T2V 14B FusionX
Wan · QuantStack
Params14.3B
Context—
Q4_K_M9.7 GB
GGUF
OC
Occamy 1.0
Occamy · bartowski
Params34.7B
Context256K
Q4_K_M22.3 GB
Tool useVision
QW
Bella Bartender Qwen3.5 2b
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool use

Other quants

Keep browsing