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-Vl-2B-Thinking
Qwen · unsloth
Params1.72B
Context256K
Q4_K_M1.1 GB
ReasoningVision
RO
TheDrummer Rocinante XL 16B v1
Rocinante · bartowski
Params16.1B
Context128K
Q4_K_M10.1 GB
GGUF
MI
Minimax-M3
Minimax · unsloth
Params426B
Context1024K
Q4_K_M264.9 GB
Vision
MA
Magnum v4 72b
Magnum · bartowski
Params72.7B
Context32K
Q4_K_M47.4 GB
GGUF
QW
Qwen3-235B-A22B-Instruct-2507
Qwen · unsloth
Params235B
Context256K
Q4_K_M142.2 GB
GGUF
QW
Qwen2.5 VL 3B Instruct
Qwen · mradermacher
Params3.09B
Context125K
Q4_K_M1.9 GB
Vision
XI
Xing4.0 29B A4B
Xing · XingChen-AGI
Params31.2B
Context256K
Smallest0.2 GB
GGUF
OR
Ornith 1.5 9b Mtp
Ornith · protoLabsAI
Params456M
Context256K
Q4_K_M5.8 GB
Vision
LY
Lythri 4B A2B
Lythri · bartowski
Params4.63B
Context128K
Q4_K_M3.2 GB
GGUF
GL
GLM 5
GLM · unsloth
Params754B
Context198K
Q4_K_M455.9 GB
GGUF
DE
WhiteRabbitNeo WhiteRabbitNeo V3 7B
Deephat · bartowski
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
GE
Gemma 4 12B HybridAgent
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
ReasoningTool use
QW
Qwen3 32B Uncensored
Qwen · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
GGUF
QW
Qwen3 VL 8B Heretic Stable
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Vision
LL
Llama 3.2 8X4B MOE V2 Dark Champion Instruct uncensored abliterated 21B
Llama · DavidAU
Params20.9B
Context128K
Q4_K_M12.9 GB
Roleplay
GL
Glm-4-9B-0414
GLM · unsloth
Params9.4B
Context32K
Q4_K_M6.2 GB
GGUF
GR
Granite 20b Code Instruct
Granite · bartowski
Params20B
Context8K
Q4_K_M12.8 GB
CodingTool use
GE
Fallen Gemma3 27B v1
Gemma · bartowski
Params27B
Context128K
Q4_K_M16.5 GB
GGUF
HO
K2-Horizon-MoVA-36B-A4B
Horizon · mradermacher
Params37.4B
Context512K
Q4_K_M22.4 GB
GGUF
QW
Qwen3 8B Heretic
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
QW
Qwen3.5 9B Coder
Qwen · mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
CodingReasoningTool use
MI
Mistral Small 3.1 24B Instruct 2503
Mistral · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB
Vision
MI
Ministral-3-14B-Reasoning-2512
Mistral · unsloth
Params13.5B
Context256K
Q4_K_M8.2 GB
ReasoningVision
ST
StartLux Decision 35B A3B
Startlux · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
Vision
MA
UI Mate 9B
Mate · bartowski
Params8.95B
Context256K
Q4_K_M5.9 GB
Vision
QW
Qwen3-Coder-480B-A35B-Instruct
Qwen · unsloth
Params480B
Context256K
Q4_K_M290.1 GB
Coding
GE
Gemma 2 27b It
Gemma · legraphista
Params27.2B
Context8K
Smallest6.1 GB
GGUF
DE
DeepSeek R1 Distill Llama 70B Abliterated
DeepSeek · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
Reasoning
FA
Fara1.5 9B
Fara · bartowski
Params8.95B
Context256K
Q4_K_M5.9 GB
Vision
MI
MiniCPM V 4.7 1B heretic
MiniCPM · saidutta69
Params1.01B
Context256K
Q4_K_M0.7 GB
ReasoningRoleplayTool use

Other quants

Keep browsing