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
BE
Behemoth X 123B v2.1
Behemoth · bartowski
Params123B
Context128K
Q4_K_M73.2 GB
GGUF
RO
Rocinante X 12B v1 Heretic Uncensored
Rocinante · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
DE
Deepseek-Prover-V2-671B-Bf16
DeepSeek · unsloth
Params671B
Context160K
Q4_K_M404.5 GB
Coding
AV
Average_Normie_v3.69_8B
Average · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
GE
Gemma 4 A4B 98e v6 Coder It
Gemma · ManniX-ITA
Params19.9B
Context256K
Q4_K_M10.6 GB
CodingVision
NU
NuMarkdown-8B-Thinking
Numarkdown · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
ReasoningVision
WR
Wraith 8b
Wraith · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
ReasoningRoleplay
QW
Qwen3.5 2B GPT 5.1 HighIQ INSTRUCT
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
Reasoning
MU
Muslim 6B v3
Muslim · mradermacher
Params5.94B
Context256K
Q4_K_M3.7 GB
Tool use
ST
MN 12B Starcannon v1 i1
Starcannon · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
NE
Next2.5
Next · thelamapi
Params4.2B
Context256K
Q4_K_M2.7 GB
ReasoningVision
DQ
dqnMath v1
Dqnmath · mradermacher
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
LL
Infinity-Instruct-3M-0613-Llama3-70B
Llama · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
PY
Pyrz 8B Instruct Uncensored i1
Pyrz · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
GR
Granite-4.1-30B
Granite · unsloth
Params28.9B
Context128K
Q4_K_M17.5 GB
GGUF
OZ
Ozyvler Ozygram Neural 7B Coder MCTS
Ozyvler · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
LL
CodeLlama 13b Python Hf
Llama · mradermacher
Params13B
Context16K
Q4_K_M7.9 GB
Coding
QW
Qwen3 Esper3 Reasoning CODER Instruct 12B Brainstorm20x
Qwen · mradermacher
Params11.9B
Context40K
Q4_K_M7.2 GB
CodingReasoning
QW
Qwen3 VL 12B Instruct Brainstorm20x
Qwen · mradermacher
Params11.9B
Context256K
Q4_K_M7.2 GB
CodingVision
KA
Karnak
Karnak · mradermacher
Params40.7B
Context256K
Q4_K_M24.7 GB
Tool use
DE
Ph3della 14B i1
Della · mradermacher
Params14B
Context4K
Q4_K_M8.6 GB
GGUF
LO
Loopl Vl 4b
Loopl · mradermacher
Params4B
Context256K
Q4_K_M2.5 GB
Tool useVision
HO
Holo2 235B A22B
Holo · mradermacher
Params235B
Context256K
Q4_K_M142.2 GB
GGUF
EU
EuroLLM 9B MeditronFO
Eurollm · mradermacher
Params9.15B
Context4K
Q4_K_M5.6 GB
GGUF
PY
Pygmalion 3 12B
Pygmalion · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
Roleplay
ME
Medra27B
Medra · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
Reasoning
SP
Spark-X2.5-1.7B
Spark · Mungert
Params1.71B
Context1024K
Q4_K_M1.1 GB
GGUF
QW
Qwen3 30B A3B Instruct 2507 REAM Heretic
Qwen · mradermacher
Params23.3B
Context256K
Q4_K_M14.2 GB
GGUF
QW
Qwen3 235B A22B Thinking 2507
Qwen · bartowski
Params235B
Context256K
Q4_K_M142.6 GB
Reasoning
CY
Cydonia 24B v4.3 Heretic v3
Cydonia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Coding

Other quants

Keep browsing