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.
GE
gemma-2-9b-it
Gemma · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
ME
G4 MeroMero 31B
Meromero · zerofata
Params30.7B
Context256K
Q4_K_M18.7 GB
MA
Magidonia 24B v4.3
Magidonia · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB
GR
Grok 1
Grok · Arki05
Params316B
Context8K
Smallest65.3 GB
SA
Sao10K L3 8B Stheno v3.1
Sao · RichardErkhov
Params8B
Context—
Q4_K_M0.3 GB
GL
GLM 4.7 Flash
GLM · bartowski
Params30B
Context198K
Q4_K_M18.5 GB
GE
gemma 4 12B it
Gemma · AtomicChat
Params11.9B
Context256K
Q4_K_M7.4 GB
QW
Huihui Qwen3 30B A3B Instruct 2507 Abliterated
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
QW
Qwen3 Coder Next Abliterated
Qwen · bartowski
Params79.7B
Context256K
Q4_K_M48.6 GB
QW
Qwen3 14B Abliterated
Qwen · bartowski
Params14.8B
Context40K
Q4_K_M9.0 GB
QW
Qwen3.5-27B-Uncensored-HauhauCS-Aggressive
Qwen · HauhauCS
Params27B
Context256K
Q4_K_M16.5 GB
GE
gemma 4 E4B it
Gemma · AtomicChat
Params7.52B
Context128K
Q4_K_M5.3 GB
GL
GLM 5.3 Flash CYBERSECURITY
GLM · SyndicateLabs
Params313B
Context1024K
Q4_K_M195.5 GB
QW
Qwen3 VL 8B Instruct
Qwen · bartowski
Params8.19B
Context256K
Q4_K_M5.0 GB
QW
Qwen3.6 27B A3B Coder
Qwen · ManniX-ITA
Params26.2B
Context256K
Q4_K_M14.7 GB
QW
Qwen3 14B
Qwen · bartowski
Params14.8B
Context32K
Q4_K_M9.0 GB
MI
Dolphin3.0 Mistral 24B
Mistral · bartowski
Params23.6B
Context32K
Q4_K_M14.3 GB
QW
Qwen2.5 Math 1.5B Instruct
Qwen · bartowski
Params1.54B
Context4K
Q4_K_M1.0 GB
GE
Gemma 4 Novelist Eclipse 31B
Gemma · bartowski
Params32.1B
Context256K
Q4_K_M20.4 GB
QW
SpaceTimee/Suri-Qwen-3.8-27B-Uncensored
Qwen · SpaceTimee
Params27.3B
Context256K
Q4_K_M16.5 GB
GE
UNSEEN Gemma 4 26B NSFW
Gemma · Jommarn
Params25.2B
Context256K
Q4_K_M16.8 GB
DE
DeepSeek R1 Distill Qwen 32B Abliterated
DeepSeek · bartowski
Params32.8B
Context128K
Q4_K_M19.9 GB
LF
LFM2.5 1.2B Instruct
Lfm · bartowski
Params1.17B
Context125K
Q4_K_M0.7 GB
MA
MN 12B Mag Mell R1
Mag · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
MI
avemio digital mistral 7b Sft pretrain 6000 steps merge
Mistral · RichardErkhov
Params7.24B
Context—
Q4_K_M0.1 GB
QW
XORTRON RICO v3
Qwen · darkc0de
Params27.3B
Context256K
Q4_K_M16.8 GB
QW
Qwen3 0.6b Abliterated
Qwen · mradermacher
Params596M
Context40K
Q4_K_M0.4 GB
NE
NeoHorse 1 4B
Neohorse · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
MU
Muse Glimmer 30B
Muse · bartowski
Params27.9B
Context128K
Q4_K_M17.3 GB
DE
DeepSeek R1 0528
DeepSeek · bartowski
Params670B
Context160K
Q4_K_M409.2 GB