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
VI
VibeThinker 3B
Vibethinker · mradermacher
Params3.09B
Context128K
Q4_K_M1.9 GB
CodingReasoning
QW
Qwen3.5 9B Claude Fable 5xMerge
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoning
GL
GLM-ASR-Nano-2512
GLM · Mungert
Params1.59B
Context8K
Q4_K_M1.1 GB
GGUF
KU
Kunokukulemonchini 7b
Kunokukulemonchini · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
GGUF
TO
TooManyMixRolePlay-7B-Story_V3.5
Toomanymixroleplay · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
QW
Ministral 3 3B Qwen3.8 Max Reasoning Distilled
Qwen · mradermacher
Params3.43B
Context256K
Q4_K_M2.1 GB
ReasoningTool use
AE
Aetheria L2 70B i1
Aetheria · mradermacher
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
GE
Gemma 3 1b It Heretic Extreme Uncensored Abliterated
Gemma · mradermacher
Params1B
Context32K
Q4_K_M0.8 GB
GGUF
NO
Noema 1.5 4B Fast
Noema · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
CodingReasoning
HE
Hermes 4 14B
Hermes · gabriellarson
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningRoleplayTool use
MI
TowerInstruct Mistral 7B v0.2
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
AR
Artemis 31B v1
Artemis · bartowski
Params30.7B
Context256K
Q4_K_M19.6 GB
Vision
LF
LFM2 VL 450M
Lfm · bartowski
Params354M
Context125K
Q4_K_M0.2 GB
Vision
GL
glm-4-9b-chat
GLM · legraphista
Params9.4B
Context128K
Smallest3.1 GB
GGUF
PY
Pythia 410m
Pythia · mradermacher
Params405M
Context2K
Q4_K_M0.3 GB
GGUF
NO
Nock Coder 1.5b
Nock · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
Coding
JE
Jebadiah 27b v2 1
Jebadiah · bartowski
Params27.3B
Context256K
Q4_K_M17.4 GB
Vision
LL
Humanish Roleplay Llama 3.1 8B i1
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Roleplay
NE
Neuralgamma 2.5 7B slerp
Neuralgamma · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
Tool use
QW
Qwen3.8 4B Agentic Distill
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
GGUF
FR
FrogNano 4B 2609
Frognano · mradermacher
Params4.33B
Context256K
Q4_K_M2.8 GB
GGUF
ED
EduMixtral 4x7B i1
Edumixtral · mradermacher
Params24.2B
Context32K
Q4_K_M14.6 GB
GGUF
VI
Vikhr Nemo 12B Instruct R 21 09 24
Vikhr · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
MI
Mahou-1.2a-mistral-7B
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
CH
Chiboard 1.1 0.8b
Chiboard · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
GE
Huihui Gemma 4 31B It Abliterated v2
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
GGUF
HE
HERO 4B
Hero · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
GGUF
DE
FuseO1 DeepSeekR1 Qwen2.5 Coder 32B Preview v0.1
DeepSeek · bartowski
Params32.8B
Context128K
Q4_K_M19.9 GB
Coding
MP
Mpt 30b Instruct
Mpt · mradermacher
Params30B
Context8K
Q4_K_M19.1 GB
GGUF
NO
Nous Puffin 70B i1
Nous · mradermacher
Params69B
Context4K
Q4_K_M41.4 GB
GGUF

Other quants

Keep browsing