IQ4_XS GGUF models

Importance-matrix 4-bit quant, extra small. Small files with good quality for the size. 97368 models have a IQ4_XS file. Sizes run from 1M to 2450B parameters. The longest trained context is 102400K tokens.

Most downloadedNewestLargestLongest contextSmallest
CO
CorticalStack neurotic crown clown 7b ties
Corticalstack · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
Llama Phi 3 DoRA i1
Llama · mradermacher
Params3.82B
Context4K
Q4_K_M2.3 GB
GGUF
NE
Apriel Nemotron 15b Thinker
Nemotron · bartowski
Params15B
Context64K
Q4_K_M9.1 GB
Reasoning
QW
Qwen3.5 4B MultiDistill 3xMerge UNCENSORED Heretic
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningVision
SK
Skywork SWE 32B
Skywork · bartowski
Params32.8B
Context32K
Q4_K_M19.9 GB
GGUF
OX
OxCoder 9B
Oxcoder · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Coding
NO
Nous Capybara 34B i1
Nous · mradermacher
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
US
UserLM 8b
Userlm · bartowski
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
GE
Docto Decision Gemma 4 E4B Fr v0.1
Gemma · mradermacher
Params7.52B
Context128K
Q4_K_M5.3 GB
ReasoningTool useVision
RI
Rivermind 12B v1
Rivermind · bartowski
Params12.2B
Context128K
Q4_K_M7.5 GB
GGUF
MI
Pixtral 12B Ollama
Mistral · EnlistedGhost
Params12.2B
Context1000K
Q4_K_M7.5 GB
Vision
AU
Aurelian v0.5 70b Rope8 32K Fp16
Aurelian · mradermacher
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
JA
Jais Adapted 70b Chat
Jais · RichardErkhov
Params69.5B
Context4K
Q4_K_M41.8 GB
GGUF
LA
latxa-70b-v1.2
Latxa · mradermacher
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
CH
MN CharThink 12B Base
Charthink · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
ON
OneJev 0.8B
Onejev · mradermacher
Params1.01B
Context256K
Q4_K_M0.7 GB
Vision
FU
FuseChat-Kunoichi-10.7B
Fusechat · mradermacher
Params10.7B
Context8K
Q4_K_M6.5 GB
GGUF
TH
TheSpice 7b FT ExperimentalOrca
Thespice · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
GGUF
OP
OpenCodeInterpreter-DS-6.7B
Opencodeinterpreter · RichardErkhov
Params6.74B
Context16K
Q4_K_M4.1 GB
GGUF
LL
ShiningValiantXS i1
Llama · mradermacher
Params13B
Context4K
Q4_K_M8.4 GB
GGUF
MI
OpenChat 3.5 7B Mixtral v2.0 i1
Mistral · mradermacher
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
MI
MiniCPM5-2B
MiniCPM · Mungert
Params2.52B
Context128K
Q4_K_M1.7 GB
CodingTool use
QW
calme 2.1 qwen2 72b
Qwen · MaziyarPanahi
Params72.7B
Context32K
Q4_K_M47.4 GB
GGUF
SE
Serenity 12B
Serenity · ReadyArt
Params11.9B
Context256K
Q4_K_M7.4 GB
Roleplay
QW
Qwen3 16B A3B
Qwen · bartowski
Params16B
Context40K
Q4_K_M9.8 GB
GGUF
AR
arco reasoner i1
Arco · mradermacher
Params514M
Context8K
Q4_K_M0.3 GB
GGUF
PE
Q3 30b A3b Pentiment
Pentiment · bartowski
Params30.5B
Context32K
Q4_K_M18.6 GB
Roleplay
HE
Hemmingway 1.5 Unlocked
Hemmingway · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool useVision
DE
Decka 4B
Decka · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool use
QW
Qwen3 14B RefusalDirection ThinkingAware
Qwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
Reasoning

Other quants

Keep browsing