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.

Most downloadedNewestLargestLongest contextSmallest
JI
jina embeddings v4 text matching
Jina · jinaai
Params3.1B
Context125K
Q4_K_M1.9 GB
Embedding
QW
Qwen3 4B Hivemind Instruct Heretic Abliterated Uncensored NEO Imatrix
Qwen · DavidAU
Params4B
Context256K
Q4_K_M2.5 GB
Roleplay
QW
Qwen3.8 27B Uncensored Chinese
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
GGUF
KE
Kev-9B Artemis 4.1GB
Kev · turintech
Params8.96B
Context256K
Smallest4.1 GB
ReasoningTool use
KA
Kainaticulous Rp 7b
Kainaticulous · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
GE
gemma-2-9b-it
Gemma · legraphista
Params9.24B
Context8K
Smallest2.4 GB
GGUF
GL
GLM 4.6V
GLM · mradermacher
Params107B
Context128K
Q4_K_M70.4 GB
GGUF
GR
Granite 3b Code Base 2k
Granite · mradermacher
Params3.48B
Context2K
Q4_K_M2.1 GB
Coding
NY
Nyakura CausalLM RP 34B i1
Nyakura · mradermacher
Params34.4B
Context195K
Q4_K_M20.7 GB
Roleplay
TA
UI TARS 7B DPO
Tars · bartowski
Params7.62B
Context32K
Q4_K_M4.7 GB
Vision
MI
Mixtral_7Bx2_MoE_13B
Mistral · mradermacher
Params12.9B
Context32K
Q4_K_M7.8 GB
GGUF
MI
Sydney_Pirate_Mistral_7b
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
CodeLlama 70b Instruct Hf
Llama · mradermacher
Params69B
Context4K
Q4_K_M41.4 GB
Coding
ST
StarCoder
StarCoder · mradermacher
Params15.5B
Context8K
Q4_K_M10.0 GB
Coding
HO
Holo4 35B A3B
Holo · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
BO
Boulesis v2.1 26B A4B HeadTune
Boulesis · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
ReasoningRoleplayTool use
MI
ANITA NEXT 24B Dolphin Mistral UNCENSORED ITA
Mistral · mradermacher
Params23.6B
Context40K
Q4_K_M14.3 GB
Reasoning
NE
NVIDIA Nemotron 3.5 Bolt E4B
Nemotron · bartowski
Params7.52B
Context64K
Q4_K_M5.2 GB
ReasoningTool useVision
QW
Swift 1.5 Qwen3.8 27b Heretic
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
Vision
DI
digital socrates 7b i1
Digital · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
GE
Mahou-1.3-gemma2-9B
Gemma · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
DE
MultiPL-T-DeepSeekCoder_33b
DeepSeek · mradermacher
Params33.3B
Context16K
Q4_K_M19.9 GB
Coding
AU
Aura Prototype 26B A4B
Aura · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
Roleplay
PE
PentaCoder 9B
Pentacoder · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoning
LF
LFM2.5-24B-A2B-Preview
Lfm · AtomicChat
Params24B
Context128K
Q4_K_M15.4 GB
ReasoningTool use
GR
Granite 20b Code Instruct
Granite · legraphista
Params20B
Context8K
Smallest4.5 GB
CodingTool use
GR
Granite 8b Code Base 128k
Granite · RichardErkhov
Params8.05B
Context125K
Q4_K_M4.9 GB
Coding
NE
Nemomix v4.0 12B
Nemomix · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
EA
EAN 8B i1
Ean · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool use
LF
Atomic Chat / LFM2.5 8B A1B
Lfm · AlexAtomic
Params8.47B
Context125K
Q4_K_M5.2 GB
GGUF

Other quants

Keep browsing