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.
BO
Borealis 12b
Borealis · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
CY
CyberStag Security 26B A4B V1 Uncensored Heretic
Cyberstag · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
LL
Llama 3.2 1B Instruct
Llama · DavidAU
Params1.24B
Context128K
Q4_K_M0.8 GB
AU
AuroraCap 7B IMG xtuner i1
Auroracap · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
YO
Yousei-22B
Yousei · mradermacher
Params21.8B
Context4K
Q4_K_M13.2 GB
LL
llama-3-70B-Instruct-abliterated
Llama · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
YI
Configurable-Yi-1.5-9B-Chat
Yi · mradermacher
Params8.83B
Context4K
Q4_K_M5.3 GB
MI
Mistral Small 3.2 24B Instruct 2506 Absolute Heresy
Mistral · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
YI
Yi-34B-Chat
Yi · mradermacher
Params34.4B
Context4K
Q4_K_M20.7 GB
NE
Dory1.0 4B BF16 Llamacpp
Nemotron · cloudnathan5
Params3.98B
Context256K
Q4_K_M2.4 GB
QW
Qwen3.8 27B Ultra Uncensored Heretic Native MTP Preserved
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
CY
Cydonia R1 24B v4
Cydonia · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB
LL
hon9kon9ize Cantonese Llama 2 7B preview20240625
Llama · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
BA
Basal Omni 1.0 Ultra
Basal · bartowski
Params30.7B
Context256K
Q4_K_M19.5 GB
MI
Mistral 7B Instruct v0.2
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
DA
Dans PersonalityEngine v1.0.0 8b
Dans · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
NE
NeuralArjuna 7B DT
Neuralarjuna · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
GE
Amoral Gemma3 12B v2
Gemma · bartowski
Params11.8B
Context128K
Q4_K_M7.3 GB
QW
Qwen2.5 32B Instruct Abliterated
Qwen · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
PH
FC PHI 3.5 Mini Merged 1
Phi · mradermacher
Params3.82B
Context128K
Q4_K_M2.3 GB
MY
MythoMax L2 13b i1
Mythomax · mradermacher
Params13B
Context4K
Q4_K_M8.1 GB
LL
SEVENLLM-Llama2-7B-CoT
Llama · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
QW
Qwen2.5 7B Instruct Abliterated v2
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GL
GLM Z1 Rumination 32B 0414
GLM · bartowski
Params33.1B
Context128K
Q4_K_M20.0 GB
MI
Dolphin-Mistral-24B-Venice-Edition
Mistral · Mungert
Params23.6B
Context32K
Q4_K_M14.5 GB
DE
DeepSeek R1 0528 Qwen3 8B Heretic
DeepSeek · mradermacher
Params8.19B
Context128K
Q4_K_M5.0 GB
LL
llm jp 3.1 13b instruct4
Llm · mmnga
Params13.7B
Context4K
Q4_K_M8.3 GB
QW
OpenSpatial Qwen2.5 VL 7B
Qwen · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
QW
Qwen3.6 27B Fable Fusion 711 Uncensored Heretic NM DAU NEO MAX MTP
Qwen · tatekuperus
Params27B
Context256K
Q4_K_M18.0 GB
QW
Qwen2.5 72B
Qwen · mradermacher
Params72.7B
Context128K
Q4_K_M47.4 GB