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
QW
ThinkingCap Qwen3.6 27B
Qwen · bartowski
Params27.3B
Context256K
Q4_K_M17.8 GB
ReasoningVision
CO
ConfigurableSOLAR 10.7B i1
Configurablesolar · mradermacher
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
QW
Qwepus
Qwepus · mradermacher
Params8.95B
Context1024K
Q4_K_M5.6 GB
Coding
QW
Qwen3.6 27B Omnimerge v4
Qwen · ManniX-ITA
Params27B
Context256K
Q4_K_M16.5 GB
CodingReasoningVision
LL
Llama 3.3 70B Instruct
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
LL
UCCIX Llama2 13B i1
Llama · mradermacher
Params13.1B
Context4K
Q4_K_M7.9 GB
GGUF
DA
daybreak kunoichi dpo 7b
Daybreak · mradermacher
Params7.24B
Context16K
Q4_K_M4.5 GB
GGUF
LI
Ling 3.0 Flash Heretic
Ling · mradermacher
Params127B
Context256K
Q4_K_M77.0 GB
GGUF
FA
FashionGPT 70B V1 i1
Fashiongpt · mradermacher
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
LL
Na0s Llama 3.1 8b Pruned 4 Layers
Llama · RichardErkhov
Params6.94B
Context128K
Q4_K_M4.3 GB
GGUF
RE
ReFeed 8B
Refeed · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
QW
Qwen3.8 27B TURBO Fable Cold Fusion 735 882 Heretic Uncensored NEO CODER MAX MTP
Qwen · Notyourmom1
Params27B
Context256K
Q4_K_M18.0 GB
CodingReasoningRoleplay
BE
Behemoth X 123B v2.2
Behemoth · mradermacher
Params123B
Context128K
Q4_K_M73.2 GB
GGUF
GE
Gemma 3 4b it MAX HORROR Uncensored DBL X Imatrix
Gemma · DavidAU
Params4.26B
Context128K
Q4_K_M3.5 GB
Roleplay
IN
INTELLECT 1 Instruct
Intellect · bartowski
Params10.2B
Context8K
Q4_K_M6.2 GB
Coding
TI
Tinyllama-Cinder-1.3B-Reason-Test
Tinyllama · RichardErkhov
Params1.28B
Context2K
Q4_K_M0.8 GB
GGUF
GE
Gemma4 Gutenberg 31B Heretic
Gemma · bartowski
Params30.7B
Context256K
Q4_K_M19.6 GB
Vision
DA
MN Dark Horror The Cliffhanger 18.5B
Dark · DavidAU
Params18.5B
Context1000K
Q4_K_M11.2 GB
Roleplay
PH
Phi 3 mini 128k instruct imatrix
Phi · duyntnet
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
MI
llava v1.6 mistral 7b
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
Vision
LL
Llama 3.2 1B Instruct Abliterated
Llama · mradermacher
Params1.5B
Context128K
Q4_K_M1.0 GB
GGUF
MU
Muse Glimmer 30B Uncensored Heretic
Muse · mradermacher
Params27.9B
Context128K
Q4_K_M16.9 GB
Vision
MI
Ministral-3-8B-Reasoning-2512
Mistral · Mungert
Params8.5B
Context256K
Q4_K_M5.5 GB
Reasoning
SP
Spark X2.5 4B
Spark · mradermacher
Params4.11B
Context1024K
Q4_K_M2.6 GB
GGUF
SE
Semancer 12B
Semancer · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
GGUF
MI
Young Children Storyteller Mistral 7B
Mistral · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen3 Coder 30B A3B IT Heretic
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
Coding
HE
Hemmingway 1.5
Hemmingway · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
HO
K2-Horizon-3.7B
Horizon · mradermacher
Params5.06B
Context512K
Q4_K_M3.2 GB
GGUF
PH
Phi 3.5 Mini 3.8B ArliAI RPMax v1.1
Phi · bartowski
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF

Other quants

Keep browsing