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
PS
Psyonic-Rose-20B-Higher-Quality
Psyonic · mradermacher
Params20B
Context4K
Q4_K_M12.0 GB
GGUF
QW
Qwen2.5 32B
Qwen · bartowski
Params32.8B
Context128K
Q4_K_M19.9 GB
GGUF
QW
QwQ 32B Preview
Qwen · bartowski
Params32.8B
Context32K
Q4_K_M19.9 GB
Reasoning
CO
CodeQwen1.5-7B
Codeqwen · bartowski
Params7.25B
Context64K
Q4_K_M4.7 GB
GGUF
IN
Inv Konstanta V4 Alpha 7B
Inv · RichardErkhov
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
BL
BlackMagic-7B
Blackmagic · mradermacher
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
PY
Pythia 1b
Pythia · mradermacher
Params1.01B
Context2K
Q4_K_M0.7 GB
GGUF
MI
T3Q Mistral Orca Math DPO
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
GGUF
QW
Qwen2.5 Furry 7B
Qwen · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
Roleplay
QW
Haru Qwen3 4b
Qwen · mradermacher
Params4B
Context256K
Q4_K_M2.5 GB
Roleplay
MI
ANIMA Cognitive Mistral v1 i1
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ST
Step 5 Preview
Step · smalinin
Params601B
Context1024K
Smallest1.2 GB
GGUF
GL
LFM2 12B A1B GLM 4.7 Thinking Quantum IQ1C P TR1 S2
GLM · mradermacher
Params11.3B
Context125K
Q4_K_M6.8 GB
CodingReasoningRoleplay
AH
Ahma-3B
Ahma · mradermacher
Params3.63B
Context2K
Q4_K_M2.8 GB
GGUF
EQ
Equinox 31B
Equinox · bartowski
Params30.7B
Context256K
Q4_K_M19.6 GB
RoleplayVision
LL
CodeLlama 7b Python Hf
Llama · mradermacher
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
ME
Merlin Agent
Merlin · bartowski
Params8.95B
Context256K
Q4_K_M5.9 GB
Coding
GL
Huihui GLM 4.6V Flash Abliterated
GLM · seanbailey518
Params9.4B
Context128K
Q4_K_M6.2 GB
Vision
NE
NVIDIA Nemotron Nano 12B v2
Nemotron · bartowski
Params12.3B
Context1024K
Q4_K_M7.5 GB
GGUF
CO
Codeqwen3 14b
Codeqwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
CodingReasoning
LL
Phind CodeLlama 34B v2
Llama · mradermacher
Params33.7B
Context16K
Q4_K_M20.2 GB
Coding
QW
OPSD Qwen3 8B
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
OP
OpenELM-270M-Instruct
Openelm · RichardErkhov
Params272M
Context2K
Q4_K_M0.2 GB
GGUF
RA
RakutenAI 7B
Rakutenai · mradermacher
Params7.37B
Context32K
Q4_K_M4.5 GB
GGUF
LL
WizardLM Mistral CodeLlama 7b
Llama · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Coding
LL
Llama 3.1 Nemotron 70B Instruct HF i1
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
MI
Magistral Small 2506
Mistral · bartowski
Params23.6B
Context32K
Q4_K_M14.3 GB
Reasoning
MI
NousResearch DeepHermes 3 Mistral 24B Preview
Mistral · bartowski
Params23.6B
Context32K
Q4_K_M14.3 GB
ReasoningRoleplayTool use
TI
TigerCoder 12B
Tigercoder · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
Coding
PR
PromptEnhancer 32B
Promptenhancer · mradermacher
Params32.8B
Context125K
Q4_K_M19.9 GB
GGUF

Other quants

Keep browsing