IQ3_XXS GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 28129 models have a IQ3_XXS file. Sizes run from 2M to 2450B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
DR
DrakIdol Roleplayer 1.0
Drakidol · mradermacher
Params3.88B
Context128K
Q4_K_M2.5 GB
Roleplay
AT
Athene codegemma 2 7b it alpaca v1.3 i1
Athene · mradermacher
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
MI
Magistral Small 2507
Mistral · bartowski
Params23.6B
Context40K
Q4_K_M14.3 GB
Reasoning
QW
jinaai/test-qwen25-coder-jina-code-embeddings-1.5b
Qwen · jinaai
Params1.54B
Context32K
Smallest0.4 GB
CodingEmbedding
PO
Polaris VGA 27B Post1.0e
Polaris · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
GE
Amoral Gemma3 12B
Gemma · bartowski
Params11.8B
Context128K
Q4_K_M7.3 GB
Roleplay
ST
Starcoderbase
StarCoder · mradermacher
Params15.8B
Context8K
Q4_K_M10.1 GB
Coding
OP
Openhands Lm 32b v0.1
Openhands · bartowski
Params32.8B
Context32K
Q4_K_M19.9 GB
GGUF
QW
Qwen3-Vl-4B-Thinking-1M
Qwen · unsloth
Params4B
Context977K
Q4_K_M2.5 GB
ReasoningVision
DO
DonutHole-8x7B
Donuthole · mradermacher
Params46.7B
Context32K
Q4_K_M28.4 GB
GGUF
QW
Qwen3 coder REAP 25B A3B Rust
Qwen · Em-80
Params25B
Context256K
Q4_K_M15.1 GB
Coding
LL
Hermes 2 Theta Llama 3 70B
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
LL
DeepHermes 3 Llama 3 8B Preview
Llama · mradermacher
Params16.5B
Context128K
Q4_K_M10.0 GB
ReasoningTool use
QW
Qwen3.5 40B RoughHouse Claude 4.6 Opus Polar Deckard Uncensored Heretic Thinking
Qwen · mradermacher
Params39.1B
Context256K
Q4_K_M23.9 GB
CodingReasoningRoleplay
MI
Mistral Small 24B Instruct 2501 Heretic
Mistral · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
LI
Lil Beastie 4b
Lil · mradermacher
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
WA
Wayfarer 2 12B
Wayfarer · LatitudeGames
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
NE
Neuron 4B Instruct
Neuron · mradermacher
Params4.02B
Context256K
Q4_K_M2.5 GB
Tool use
TO
tokyotech llm Swallow 7b instruct v0.1
Tokyotech · mmnga
Params6.83B
Context4K
Q4_K_M4.1 GB
GGUF
KI
RP King 12b
King · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
Roleplay
BO
Borealis 270m
Borealis · mradermacher
Params268M
Context32K
Q4_K_M0.3 GB
GGUF
GL
zai org GLM 5.1
GLM · bartowski
Params754B
Context198K
Q4_K_M459.7 GB
GGUF
G9
G9v3 3B
NANI-Nithin
Params3B
Context128K
Q4_K_M1.8 GB
GGUF
HU
Hunyuan 4B Instruct
Hunyuan · bartowski
Params4.22B
Context256K
Q4_K_M2.6 GB
GGUF
QW
Qwen2.5 14B Instruct Abliterated
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
GGUF
QW
calme-2.2-qwen2-72b
Qwen · bartowski
Params72.7B
Context32K
Q4_K_M47.4 GB
GGUF
GE
voxprint gemma4 31b
Gemma · Mitroshenkov87
Params30.7B
Context256K
Q4_K_M18.7 GB
GGUF
GR
Granite 4.1 8b Abliterated AND Disinhibited
Granite · mradermacher
Params8.38B
Context128K
Q4_K_M5.1 GB
GGUF
QW
QiMing Holos Plus Qwen3 8B
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
OL
Olmo-3-7B-Instruct
OLMo · Mungert
Params7.3B
Context64K
Q4_K_M4.7 GB
Tool use

Other quants

Keep browsing