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
QW
Qwen3.8 27B Heretic Uncensored MTP
Qwen · Unb0rn
Params27B
Context256K
Q4_K_M18.0 GB
CodingReasoningRoleplay
NA
NaNovel 35B A3B
Nanovel · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
LF
LFM2.5 2.6B UNCENSORED ABLITERATED PHILADELPHIA CLASS
Lfm · mradermacher
Params2.7B
Context125K
Q4_K_M1.7 GB
ReasoningTool use
IN
InverseCoder-DS-6.7B
Inversecoder · mradermacher
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
MA
MagpieLM 8B Chat v0.1 i1
Magpielm · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
NE
Nemotron 3.5 Embed 1B BF16
Nemotron · W4D
Params1.14B
Context256K
Q4_K_M0.7 GB
EmbeddingVision
LL
nvidia Llama 3 3 Nemotron Super 49B v1
Llama · bartowski
Params49.9B
Context128K
Q4_K_M30.2 GB
GGUF
AI
airoboros 34b 3.3 i1
Airoboros · mradermacher
Params34.4B
Context195K
Q4_K_M21.2 GB
RoleplayTool use
SW
Swallow MS 7b Instruct v0.1
Swallow · RichardErkhov
Params7.33B
Context4K
Q4_K_M4.4 GB
GGUF
WI
winter garden 7b alpha
Winter · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
GGUF
GE
Gemma4 Gutenberg 31B
Gemma · bartowski
Params30.7B
Context256K
Q4_K_M19.6 GB
Vision
CA
CantoneseLLM v2.0 30B A3B Thinking Chat Vector Merged
Cantonesellm · mradermacher
Params30.5B
Context40K
Q4_K_M18.6 GB
Reasoning
LL
Llama-3-8B-Instruct-MopeyMule
Llama · legraphista
Params8B
Context8K
Smallest2.0 GB
GGUF
QW
Qwen3 VL 4B Instruct Abliterated v1
Qwen · prithivMLmods
Params4B
Context256K
Q4_K_M2.5 GB
Vision
QW
Qwable v1
Qwable · bartowski
Params35.5B
Context256K
Q4_K_M21.9 GB
Tool useVision
BR
Breeze 7B 32k Instruct V1_0
Breeze · RichardErkhov
Params7.49B
Context32K
Q4_K_M4.5 GB
GGUF
NO
Noromaid 13B 0.4 DPO i1
Noromaid · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
ST
Starcoderplus
StarCoder · mradermacher
Params15.8B
Context8K
Q4_K_M10.1 GB
Coding
MO
Morpho 1.5B Distill
Morpho · mradermacher
Params1.54B
Context128K
Q4_K_M1.0 GB
GGUF
OV
OvisOCR2
Ovisocr · bartowski
Params752M
Context256K
Q4_K_M0.6 GB
Vision
LL
Meta-Llama-3-8B-Instruct-abliterated-v3
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Qwen3 32B Abliterated
Qwen · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
GGUF
QW
Qwen3 1.7b Abliterated
Qwen · mradermacher
Params1.72B
Context40K
Q4_K_M1.1 GB
GGUF
LF
LFM2.5 24B A2B Uncensored
Lfm · mradermacher
Params24B
Context128K
Q4_K_M14.5 GB
ReasoningTool use
MI
mistral 7b orpo capybara reproduction
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
GGUF
MI
Devstral Small 2507
Mistral · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB
CodingVision
LO
Loopl 0.8b
Loopl · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
Tool useVision
MI
RenCoder Ministral 8B Instruct 2410
Mistral · mradermacher
Params8B
Context32K
Q4_K_M4.9 GB
Coding
ME
Mephisto 1.0 4B
Mephisto · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
GGUF
ME
Mephisto 1.5 4B
Mephisto · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
CodingReasoning

Other quants

Keep browsing