Q4_K_XL GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 1216 models have a Q4_K_XL file. Sizes run from 1M to 2780B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3.5-27B
Qwen · unsloth
Params27.3B
Context256K
Q4_K_M17.1 GB
Vision
QW
Qwen3.8-27B
Qwen · rax4901
Params27.3B
Context256K
Q4_K_M16.6 GB
ReasoningTool useVision
QW
Qwen3.8-27B
Qwen · loscrossos
Params27.3B
Context256K
Q4_K_M16.6 GB
ReasoningTool useVision
OR
Ornith-1.5-35B
Ornith · peculiar-ragdoll
Params34.7B
Context256K
Smallest12.3 GB
GGUF
GR
Granite-4.0-H-Small
Granite · unsloth
Params32.2B
Context1024K
Q4_K_M19.6 GB
GGUF
KI
Kimi-K2-Thinking
Kimi · unsloth
Params1030B
Context256K
Q4_K_M621.2 GB
Reasoning
LL
Llama-3_3-Nemotron-Super-49B-V1_5
Llama · unsloth
Params49.9B
Context128K
Q4_K_M30.2 GB
GGUF
QW
Qwen3-30B-A3B-128K
Qwen · unsloth
Params30.5B
Context128K
Q4_K_M18.6 GB
GGUF
QW
Huihui Qwen3.8 Flash Next abliterated MTP
Qwen · htdohk
Params177B
Context256K
Q4_K_M1.9 GB
ReasoningVision
MI
Minimax-M2.5
Minimax · unsloth
Params230B
Context192K
Q4_K_M138.3 GB
GGUF
QW
Qwen3.8-27B
Qwen · LxBarn
Params27.3B
Context256K
Q4_K_M16.6 GB
Vision
GE
gemma 4 26B A4B it qat uncensored heretic UDmerge
Gemma · EZForever
Params25.2B
Context256K
Smallest14.2 GB
Vision
GE
Gemma-3-270M-It-Qat
Gemma · unsloth
Params268M
Context32K
Q4_K_M0.3 GB
GGUF
GL
Glm-4.1V-9B-Thinking
GLM · unsloth
Params9.4B
Context64K
Q4_K_M6.2 GB
ReasoningVision
HU
Hunyuan-A13B-Instruct
Hunyuan · unsloth
Params80B
Context256K
Q4_K_M48.8 GB
GGUF
MI
Mimo-Vl-7B-Rl
Mimo · unsloth
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
GL
GLM 5.3 Flash
GLM · SixVolts
Params321B
Context1024K
Smallest112.1 GB
Vision
DE
DeepSeek V3 0324 BF16
DeepSeek · unsloth
Params670B
Context160K
Q4_K_M404.4 GB
Coding
QW
Qwen3.5 4B
Qwen · dahara1
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
LF
Atomic Chat / LFM2.5 8B A1B
Lfm · AlexAtomic
Params8.47B
Context125K
Q4_K_M5.2 GB
GGUF
QW
Qwen3.8 27B Uncensored
Qwen · prakharprasad
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
MI
Mimo-V2.5
Mimo · unsloth
Params310B
Context1024K
Q4_K_M190.9 GB
Vision
QW
Qwen3.8 27B Uncensored JoyFox Aggressive
Qwen · joyfox
Params27.3B
Context256K
Q4_K_M16.5 GB
Vision
GE
Gemma-4-E4B-It
Gemma · ente-ai
Params7.5B
Context128K
Q4_K_M5.0 GB
Vision
QW
Qwen3.8-27B
Qwen · Hirt556
Params27.3B
Context256K
Q4_K_M16.6 GB
Vision
QW
SmartCode Fable 5 CoT Reasoning QKVO Qwen 3.6 27B Distilled
Qwen · mfielding92
Params27.3B
Context256K
Q4_K_M16.8 GB
CodingReasoning
BE
Beam 1.0 501B A23B
Beam · unsloth
Params501B
Context—
Smallest0.6 GB
GGUF
QW
Qwen2.5-Vl-72B-Instruct
Qwen · unsloth
Params72.7B
Context125K
Q4_K_M47.4 GB
Vision
GL
GLM 4.5
GLM · unsloth
Params358B
Context128K
Q4_K_M216.5 GB
GGUF
QW
Qwen2.5-Vl-32B-Instruct
Qwen · unsloth
Params32.8B
Context125K
Q4_K_M19.9 GB
Vision

Other quants

Keep browsing