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
Qwen3.6-35B-A3B
Qwen · Hagwell
Params34.7B
Context256K
Q4_K_M22.1 GB
ReasoningTool useVision
QW
Qwen3.6 27B Heretic
Qwen · SassyDiffusion
Params26.9B
Context256K
Q4_K_M17.4 GB
ReasoningTool useVision
QW
Qwen3-Coder-30B-A3B-Instruct
Qwen · kolya32rus
Params30.5B
Context256K
Q4_K_M18.6 GB
CodingTool use
HU
Cyber Tiel Coder 35B A3B
Huihui · ArkhAngelLifeJiggy
Params34.7B
Context256K
Q4_K_M22.1 GB
CodingReasoningTool use
QW
Qwen2.5-Vl-7B-Instruct
Qwen · divyanshugaur
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
QW
Qwen3.8-27B
Qwen · Hagwell
Params27.3B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
GE
Gemma-3-1B-It
Gemma · stratalab-org
Params1B
Context32K
Q4_K_M0.8 GB
GGUF
OR
Ornith 1.5 397B GGUF imatrix
Ornith · cdanis
Params403B
Context256K
Smallest1.1 GB
GGUF
R1
R1 1776
unsloth
Params671B
Context160K
Q4_K_M404.4 GB
CodingReasoningTool use
QW
Nodmix3.6 35B A3B
Qwen · Nodmix
Params34.7B
Context256K
Q4_K_M22.1 GB
ReasoningTool useVision
SO
sorbet v2 25m
Sorbet · CodeSoft
Params25M
Context4K
Smallest0.0 GB
GGUF
ER
Ernie-4.5-300B-A47B-Pt
Ernie · unsloth
Params299B
Context128K
Q4_K_M180.2 GB
GGUF
QW
axelle
Qwen · arvvvvvv
Params34.7B
Context256K
Q4_K_M22.0 GB
ReasoningTool useVision
QW
qwen36 27b
Qwen · AlexAtomic
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool use
GE
Huihui Gemma 4 26B A4B It Abliterated
Gemma · deewu0809
Params25.2B
Context256K
Q4_K_M16.9 GB
ReasoningTool useVision
QW
Qwen3-Coder-30B-A3B-Instruct
Qwen · brodatech
Params30.5B
Context256K
Q4_K_M18.6 GB
CodingTool use
GE
Gemma-3-12B-It
Gemma · socrate-tech
Params11.8B
Context128K
Q4_K_M7.3 GB
Vision
QW
Qwen3-Coder-30B-A3B-Instruct
Qwen · Quixote12
Params30.5B
Context256K
Q4_K_M18.6 GB
CodingTool use
CL
CLIP
Clip · f5aiteam
Params7.62B
Context125K
Q4_K_M4.7 GB
GGUF
GE
Gemma-4-E2B-It
Gemma · aoiandroid
Params4.65B
Context128K
Q4_K_M3.1 GB
ReasoningTool useVision
LL
Cogito-V2-Preview-Llama-405B
Llama · unsloth
Params406B
Context128K
Q4_K_M243.1 GB
ReasoningTool use
QW
Qwen3.5-4B
Qwen · moinulmoin
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
QW
Qwen3.8-27B
Qwen · wodheifn
Params27.3B
Context256K
Q4_K_M16.5 GB
Vision
QW
Qwen-Agentworld-35B-A3B
Qwen · vadikulous-ai
Params447M
Context256K
Smallest22.9 GB
Vision
QW
Qwen3.6-35B-A3B
Qwen · yangzikang
Params34.7B
Context256K
Q4_K_M22.1 GB
ReasoningTool useVision
GL
Glm-4.7-Flash
GLM · andrewheins55
Params29.9B
Context198K
Q4_K_M18.3 GB
ReasoningTool use
QW
SmartCode Fable 5 CoT Reasoning QVO Qwen 3.6 27B Distilled
Qwen · mfielding92
Params27.3B
Context256K
Q4_K_M16.8 GB
CodingReasoningTool use
QW
Qwen3-14B-128K
Qwen · sabine812
Params14.8B
Context128K
Q4_K_M9.0 GB
ReasoningTool use
QW
Qwen3.6-35B-A3B
Qwen · Fastiraz
Params35.5B
Context256K
Q4_K_M22.7 GB
ReasoningTool useVision
QW
Qwen3-Coder-Next
Qwen · kebengdou
Params79.7B
Context256K
Q4_K_M48.5 GB
CodingTool use

Other quants

Keep browsing