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
NE
AceReason Nemotron 1.1 7B
Nemotron · bartowski
Params7.62B
Context128K
Q4_K_M4.7 GB
CodingReasoning
MI
Luau Devstral 24B Instruct v0.2
Mistral · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Coding
SE
SenseNova U1.5 8B MoT
Sensenova · mradermacher
Params9.35B
Context256K
Q4_K_M5.7 GB
ReasoningTool use
VI
VisCoder 7B
Viscoder · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
LL
CodeLlama 13B Fireplace i1
Llama · mradermacher
Params13B
Context16K
Q4_K_M7.9 GB
CodingTool use
LL
Llama 3.2 8X3B MOE Dark Champion Instruct Uncensored Abliterated 18.4B
Llama · mradermacher
Params18.4B
Context128K
Q4_K_M11.3 GB
GGUF
MI
Mistral Medium 3.5 128B Desiccated
Mistral · mradermacher
Params125B
Context256K
Q4_K_M74.9 GB
GGUF
FI
Fimburs11V3
Fimburs · mradermacher
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
SW
Swallow MS 7b v0.1
Swallow · mradermacher
Params7.33B
Context4K
Q4_K_M4.4 GB
GGUF
CI
70B L3.3 Cirrus X1
Cirrus · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
PA
MS3.2 PaintedFantasy Visage v3 34B
Paintedfantasy · bartowski
Params34B
Context128K
Q4_K_M20.7 GB
GGUF
GE
Gemma 4 12B It Guardpoint
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
Reasoning
QW
Qwen3.5 18b A3B Reap Coding Heretic v0
Qwen · mradermacher
Params18.5B
Context256K
Q4_K_M11.4 GB
GGUF
QW
Qwen3.5 9B Claude 4.6 OS HERETIC UNCENSORED INSTRUCT
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Roleplay
IN
InternLM2
InternLM · bartowski
Params7.74B
Context32K
Q4_K_M4.7 GB
GGUF
TA
Tacit 1.7B
Tacit · bartowski
Params1.72B
Context40K
Q4_K_M1.1 GB
GGUF
LI
Liquid A1B 8B PL Coder
Liquid · mradermacher
Params8.34B
Context125K
Q4_K_M5.0 GB
Coding
QW
Qwen2.5 14B Uncensored Instruct i1
Qwen · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
GGUF
LL
Fireball Alpaca Llama3.1.08 8B Philos C R1 i1
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Reasoning
GE
Gemma 2b It
Gemma · mradermacher
Params2.51B
Context8K
Q4_K_M1.6 GB
GGUF
QW
Qwen3.8 9B Heretic Uncensored
Qwen · marafx2007
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
LL
Llama3.1 MOE 4X8B Gated IQ Multi Tier Deep Reasoning 32B
Llama · mradermacher
Params24.9B
Context128K
Q4_K_M15.2 GB
ReasoningRoleplayTool use
FA
Faithful_Thinking_with_Image
Faithful · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Reasoning
AR
AREX Base
Arex · bartowski
Params122B
Context256K
Q4_K_M74.9 GB
ReasoningTool useVision
ER
Erk 32B
Erk · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
GGUF
LL
Collaiborator MEDLLM Llama 3 8B v1 i1
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Qwen3 4B Abliterated TIES
Qwen · mradermacher
Params4.02B
Context32K
Q4_K_M2.5 GB
ReasoningTool use
QW
Qwen3.5 13B Deckard Heretic Uncensored Thinking
Qwen · mradermacher
Params12.4B
Context256K
Q4_K_M7.7 GB
ReasoningRoleplay
BE
Beam 1.0 501B A23B
Beam · bartowski
Params501B
Context1024K
Q4_K_M314.5 GB
CodingReasoningTool use
EV
L3-8B-Everything-COT
Everything · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF

Other quants

Keep browsing