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
Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Heretic
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
Reasoning
IN
Index Translate 35B A3B preview
Index · IndexTeam
Params35.5B
Context256K
Q4_K_M21.7 GB
Vision
QW
Qwen3 30B A3B Abliterated
Qwen · mradermacher
Params30.5B
Context40K
Q4_K_M18.6 GB
GGUF
LL
Llama-3.1-8B-Instruct
Llama · unsloth
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
QW
Qwen2.5 VL 7B Instruct
Qwen · bartowski
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
QW
Qwen3.8 27B Uncensored FIT
Qwen · SC117
Params27B
Context256K
Smallest7.5 GB
Vision
NA
Nanbeige4.3 33B
Nanbeige · abenzerps
Params33.1B
Context512K
Smallest9.9 GB
ReasoningTool use
SM
SmolLM2 1.7B Instruct
SmolLM · bartowski
Params1.71B
Context8K
Q4_K_M1.1 GB
GGUF
KI
Kimi-K2-Instruct
Kimi · unsloth
Params1030B
Context128K
Q4_K_M620.8 GB
Coding
QW
Qwen2.5 7b Ins v3
Qwen · bartowski
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
QW
OpenYourMind Qwen3.6 35B A3B Kuato DPO Abliterated Uncensored
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
LL
Llama 3.1 8B Stheno v3.4
Llama · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
WA
WaifuGemma4 26b a4b v1 i1
Waifugemma · hiwaifu-research
Params25.2B
Context256K
Q4_K_M16.8 GB
Roleplay
QW
Qwen2.5-Omni-7B
Qwen · unsloth
Params7.62B
Context32K
Q4_K_M4.7 GB
Vision
QW
Qwen2.5 3B Instruct Abliterated
Qwen · mradermacher
Params3.4B
Context32K
Q4_K_M1.9 GB
GGUF
GE
Gemma 4 26B A4B StyleTune V2
Gemma · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
Roleplay
QW
Qwen3 VL 8B Instruct Abliterated v2.0
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool useVision
QW
Qwen3.5 9B Claude 4.6 HighIQ INSTRUCT HERETIC UNCENSORED
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningRoleplayTool use
QW
Qwen3.8 27B Omnimerge v6
Qwen · ManniX-ITA
Params27.3B
Context256K
Q4_K_M16.8 GB
Vision
QW
Qwen2.5 7B Instruct Abliterated v2
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
UN
Undi95 Emerhyst 20B
Undi · RichardErkhov
Params920M
Context—
Q4_K_M0.0 GB
GGUF
MI
Dolphin Mistral 24B Venice Edition
Mistral · douganger
Params23.6B
Context128K
Q4_K_M14.3 GB
Vision
MI
Ministral-3-14B-Instruct-2512
Mistral · unsloth
Params13.5B
Context256K
Q4_K_M8.2 GB
Vision
QW
Qwen3.5-35B-A3B
Qwen · unsloth
Params35.5B
Context256K
Q4_K_M22.6 GB
Vision
LI
Ling-3.0-flash-Sante
Ling · AtomicChat
Params127B
Context256K
Smallest35.7 GB
ReasoningTool use
ME
Medgemma-1.5-4B-It
Medgemma · unsloth
Params3.88B
Context128K
Q4_K_M2.5 GB
ReasoningVision
RO
Rocinante X 12B v1
Rocinante · bartowski
Params12.2B
Context128K
Q4_K_M7.5 GB
GGUF
NA
Nanbeige4.2 3B
Nanbeige · gkraker04
Params4.17B
Context256K
Q4_K_M2.6 GB
GGUF
GL
GLM 4 9B 0414
GLM · bartowski
Params9.4B
Context32K
Q4_K_M6.2 GB
GGUF
HO
K2 Horizon MoVA 36B A4B
Horizon · NANI-Nithin
Params37.4B
Context512K
Q4_K_M22.4 GB
Reasoning

Other quants

Keep browsing