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
MI
OpenHermes-2.5-Mistral-7B-x2
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
MI
Mahou-1.2-mistral-7B
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
DE
DeepSeek-Coder-V2-Lite-Base
DeepSeek · mradermacher
Params15.7B
Context160K
Q4_K_M10.4 GB
Coding
MI
MistralAI Magistral Small 2507 Heretic Uncensored
Mistral · mradermacher
Params23.6B
Context40K
Q4_K_M14.3 GB
ReasoningRoleplay
QW
Deductive Reasoning Qwen 32B
Qwen · bartowski
Params32.8B
Context32K
Q4_K_M19.9 GB
Reasoning
QW
Qwen2.5 Coder 1.5B Instruct Abliterated
Qwen · mradermacher
Params1.78B
Context32K
Q4_K_M1.1 GB
CodingTool use
MA
Magnum Blackout Ataraxy 2 9b i1
Magnum · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
IN
Internlm2 Math Plus 1_8b
InternLM · mradermacher
Params1.89B
Context8K
Q4_K_M1.2 GB
GGUF
AR
Artemis 31B v1.1 Heretic
Artemis · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
GGUF
QW
Qwen3.8 27B
Qwen · Distillio
Params27.3B
Context256K
Q4_K_M17.8 GB
Vision
LO
Loki v5.1 i1
Loki · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
OR
Ornstein Hermes 3.6 27b SABER
Ornstein · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool use
NE
Nemotron Cascade 2 30B A3B Heretic Ara Uncensored
Nemotron · mradermacher
Params31.6B
Context1024K
Q4_K_M24.5 GB
Reasoning
RE
Rex Frame 3B
Rex · mradermacher
Params3.09B
Context125K
Q4_K_M1.9 GB
Vision
MI
Ministral 8B Instruct 2410
Mistral · bartowski
Params8B
Context32K
Q4_K_M4.9 GB
GGUF
DO
Dolphin v2
Dolphin · prithivMLmods
Params3.1B
Context125K
Q4_K_M1.9 GB
CodingVision
SO
T3Q ko solar dpo v3.0
Solar · mradermacher
Params10.7B
Context4K
Q4_K_M6.6 GB
GGUF
MI
dolphin-2.9.1-mixtral-1x22b
Mistral · legraphista
Params22.2B
Context64K
Smallest4.8 GB
CodingTool use
JI
JiRackUltra_7b
Jirackultra · mradermacher
Params7.6B
Context128K
Q4_K_M4.7 GB
Tool use
LL
Llama 3.1 8B Reason Blend 888k i1
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
ZE
Zen3 Vl
Zen · mradermacher
Params8.2B
Context256K
Q4_K_M5.0 GB
Vision
KA
Kalypso
Kalypso · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
Roleplay
QW
Qwen3.5 9B Brainwaves OneJev1.6
Qwen · mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
ReasoningTool use
GR
Grug 27b
Grug · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
ReasoningTool use
AR
Aryabhata 2.0
Aryabhata · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
Reasoning
LU
Luminaura-RP-13B
Luminaura · mradermacher
Params13B
Context128K
Q4_K_M7.9 GB
Roleplay
LL
Llama-3-Groq-8B-Tool-Use
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
Tool use
LL
Lexi Llama 3 8B Uncensored
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
IN
InnoSpark3.1 27B 1008
Innospark · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
GGUF
MI
Mistral Nemo Instruct 2407
Mistral · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF

Other quants

Keep browsing