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
GE
Gemma 3 27b It Abliterated
Gemma · bartowski
Params27B
Context128K
Q4_K_M16.5 GB
Vision
GE
Gemma 4 Dark Orthia Untied 31B
Gemma · mradermacher
Params32.1B
Context256K
Q4_K_M19.5 GB
ReasoningTool use
RO
RoLlama2-7b-Base
Rollama · legraphista
Params6.74B
Context4K
Smallest1.5 GB
GGUF
ME
Medgemma 4b It
Medgemma · bartowski
Params3.88B
Context128K
Q4_K_M2.5 GB
ReasoningVision
GE
Gemma 4 Dark Orthia 31B
Gemma · mradermacher
Params32.1B
Context256K
Q4_K_M19.5 GB
ReasoningTool use
BA
Bathory X 26B A4B 0.2
Bathory · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
GGUF
NE
nexus finance
Nexus · King3Djbl
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
LL
FILM6912 Meta Llama 3.1 8B Instruct
Llama · RichardErkhov
Params8B
Context—
Q4_K_M0.0 GB
GGUF
WE
WestLake 10.7B v2
Westlake · backyardai
Params10.7B
Context32K
Q4_K_M6.5 GB
Roleplay
LL
Llama Artemis
Llama · mradermacher
Params8.2B
Context128K
Q4_K_M5.0 GB
GGUF
QW
dolphin-2.9.2-qwen2-72b
Qwen · bartowski
Params72.7B
Context128K
Q4_K_M47.4 GB
CodingTool use
HO
K2-Horizon-32B
Horizon · bartowski
Params34.8B
Context512K
Q4_K_M22.0 GB
GGUF
QW
Qwen3.5 27B Ultra Uncensored Heretic v2
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
GO
Goetia 26B A4B v1.3 Absolute Heretic ARA
Goetia · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
Roleplay
MI
dolphin 2.8 mistral 7b v02
Mistral · lmstudio-community
Params7.24B
Context32K
Q4_K_M4.4 GB
CodingTool use
PY
Pyrut 8B Instruct Uncensored i1
Pyrex · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
RO
RoLlama2-7b-Instruct
Rollama · legraphista
Params6.74B
Context4K
Smallest1.5 GB
GGUF
AP
Apex 35B V1.0
Apex · bartowski
Params35.5B
Context256K
Q4_K_M22.8 GB
ReasoningTool useVision
SW
Swish 31B Final
Swish · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningTool use
QW
Qwen2.5 Coder 0.5B Instruct
Qwen · bartowski
Params494M
Context32K
Q4_K_M0.4 GB
Coding
GE
Gemma 4 31B Monadize v0.1
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningTool use
GE
Gemma 4 26B A4B It Heretic
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
Coding
GE
Gemma 4 E4B Abliterated Uncensored
Gemma · mradermacher
Params7.46B
Context128K
Q4_K_M5.3 GB
Roleplay
QW
Raw Uncensored Qwen3 14b Heretic Recovered
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
GGUF
LL
Llama 3.2 1B Instruct Uncensored
Llama · mradermacher
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
HY
Hy MT2 7B
mradermacher
Params7.5B
Context256K
Q4_K_M4.6 GB
GGUF
QW
Qwen3 32B
Qwen · bartowski
Params32.8B
Context32K
Q4_K_M19.8 GB
GGUF
NE
Nex N2 Mini
Nex · bartowski
Params34.7B
Context256K
Q4_K_M21.4 GB
Vision
HE
0 hero Matter 0.2 7B
Hero · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
AR
Artoma Lexicon 31B
Artoma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
Roleplay

Other quants

Keep browsing