IQ3_M GGUF models
Importance-matrix 3-bit quant, medium. Aimed at low-memory setups. 47889 models have a IQ3_M file. Sizes run from 1M to 1030B parameters. The longest trained context is 102400K tokens.
QW
Qwen2.5 VL 7B NSFW Caption V3
Qwen · bartowski
Params7.62B
Context125K
Q4_K_M4.7 GB
PH
Phi 3 mini 4k instruct GGUF Imatrix smashed
Phi · PrunaAI
Params3.82B
Context4K
Q4_K_M2.4 GB
LU
LunaraHome 26B A4B
Lunarahome · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
GE
Gemma 4 Novelist Eclipse 31B
Gemma · mradermacher
Params32.1B
Context256K
Q4_K_M19.5 GB
OR
Ornith 1.5 122B
Ornith · bartowski
Params125B
Context256K
Q4_K_M78.9 GB
LL
Lexi-Llama-3-8B-Uncensored
Llama · bartowski
Params8B
Context8K
Q4_K_M4.9 GB
MI
Dolphin3.0 R1 Mistral 24B
Mistral · bartowski
Params23.6B
Context32K
Q4_K_M14.3 GB
QW
Qwen3.8 9B Distill Uncensored Heretic
Qwen · mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
RO
TheDrummer Rocinante XL 16B v1
Rocinante · bartowski
Params16.1B
Context128K
Q4_K_M10.1 GB
MA
Magnum v4 72b
Magnum · bartowski
Params72.7B
Context32K
Q4_K_M47.4 GB
QW
Qwen3.8 27B abliterated MTP
Qwen · hotdogs
Params27B
Context256K
Q4_K_M16.8 GB
XI
Xing4.0 29B A4B
Xing · XingChen-AGI
Params31.2B
Context256K
Smallest0.2 GB
OR
Ornith 1.5 9b Mtp
Ornith · protoLabsAI
Params456M
Context256K
Q4_K_M5.8 GB
LY
Lythri 4B A2B
Lythri · bartowski
Params4.63B
Context128K
Q4_K_M3.2 GB
DE
WhiteRabbitNeo WhiteRabbitNeo V3 7B
Deephat · bartowski
Params7.62B
Context32K
Q4_K_M4.7 GB
GE
Gemma 4 12B HybridAgent
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
GR
Granite 20b Code Instruct
Granite · bartowski
Params20B
Context8K
Q4_K_M12.8 GB
GE
Fallen Gemma3 27B v1
Gemma · bartowski
Params27B
Context128K
Q4_K_M16.5 GB
HO
K2-Horizon-MoVA-36B-A4B
Horizon · mradermacher
Params37.4B
Context512K
Q4_K_M22.4 GB
MI
Mistral Small 3.1 24B Instruct 2503
Mistral · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB
MA
UI Mate 9B
Mate · bartowski
Params8.95B
Context256K
Q4_K_M5.9 GB
GE
Gemma 2 27b It
Gemma · legraphista
Params27.2B
Context8K
Smallest6.1 GB
DE
DeepSeek R1 Distill Llama 70B Abliterated
DeepSeek · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
FA
Fara1.5 9B
Fara · bartowski
Params8.95B
Context256K
Q4_K_M5.9 GB
QW
Qwen3 VL 30B A3B Instruct
Qwen · bartowski
Params30.5B
Context256K
Q4_K_M18.6 GB
QW
Qwen2.5 14B_Uncencored
Qwen · bartowski
Params14.8B
Context128K
Q4_K_M9.0 GB
QW
Qwen3.8 9B Heretic Uncensored
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GE
gemma 4 31B it
Gemma · AtomicChat
Params30.7B
Context256K
Q4_K_M18.7 GB
QW
Qwen2.5 Coder 14B
Qwen · bartowski
Params14.8B
Context32K
Q4_K_M9.0 GB
GE
Gemma 4 31B Heretic
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB