Q3_K_XL GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 2589 models have a Q3_K_XL file. Sizes run from 30M to 1050B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3.6-35B-A3B
Qwen · MRKoma1
Params34.7B
Context256K
Q4_K_M22.1 GB
ReasoningTool useVision
QW
Nodmix3.6 27B
Qwen · Nodmix
Params26.9B
Context256K
Q4_K_M16.8 GB
Tool useVision
LL
Llama 3.2 3B Instruct
Llama · Ether4o4
Params3.61B
Context128K
Q4_K_M2.2 GB
Tool use
QW
Qwen3.6-35B-A3B
Qwen · thy025
Params35.5B
Context256K
Q4_K_M22.7 GB
ReasoningTool useVision
KI
Kimi-K2.7-Code
Kimi · SergeyKlevan
Params1030B
Context256K
Smallest303.9 GB
CodingReasoningTool use
GL
GLM 5.3 Flash
GLM · lausannequants
Params321B
Context1024K
Smallest93.1 GB
ReasoningTool useVision
GL
GLM 5.2
GLM · LaniakeaPH
Params754B
Context1024K
Q4_K_M465.8 GB
ReasoningTool use
QW
Qwen2.5 Coder 0.5B Instruct
Qwen · Schrst
Params494M
Context32K
Q4_K_M0.4 GB
CodingTool use
QW
Qwen3.8-27B
Qwen · huake
Params27.3B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
ME
Medgemma-27B-It
Medgemma · AestheticLabs
Params27B
Context128K
Q4_K_M16.5 GB
EmbeddingVision
MI
Ministral 3 3B Reasoning 2512
Mistral · EnlistedGhost
Params3.43B
Context256K
Q4_K_M2.2 GB
ReasoningVision
GE
Gemma-4-31B-It
Gemma · ygoayu
Params30.7B
Context256K
Q4_K_M18.3 GB
ReasoningTool useVision
QW
Qwen3.6-27B
Qwen · developerjeremylive
Params27.3B
Context256K
Q4_K_M17.1 GB
ReasoningTool useVision
QW
Qwen3.5-9B
Qwen · rfisdhef
Params8.95B
Context256K
Q4_K_M5.7 GB
ReasoningTool useVision
QW
Qwen3.6-27B
Qwen · acgs
Params26.9B
Context256K
Q4_K_M16.8 GB
ReasoningTool useVision
QW
Qwen3.6-27B
Qwen · Fastiraz
Params27.3B
Context256K
Q4_K_M17.1 GB
ReasoningTool useVision
LL
Llama 3.1 8B Lexi Uncensored
Llama · Azerty76
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
DE
Qwen3 30B A3B Thinking Deepseek Distill 2507 v3.1 V2
DeepSeek · rodrigomt
Params30.5B
Context256K
Smallest13.8 GB
ReasoningTool use
FI
firefunction-v2
Firefunction · bartowski
Params70.6B
Context8K
Q4_K_M42.5 GB
Tool use
NO
North-Mini-Code-1.0
North · brodatech
Params30.5B
Context488K
Q4_K_M19.2 GB
CodingReasoningTool use
GE
Gemma-3-12B-It
Gemma · fwwrsd
Params11.8B
Context128K
Q4_K_M7.3 GB
Vision
QW
Qwen3.6-27B
Qwen · tybuddy
Params26.9B
Context256K
Q4_K_M16.8 GB
ReasoningTool useVision
MA
Magnaraxy 9b
Magnaraxy · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
GR
Granite 3.1 2b Instruct
Granite · Dzluck
Params2.53B
Context128K
Q4_K_M1.5 GB
Tool use
GE
gemma 4 it
Gemma · tripolskypetr
Params30.7B
Context128K
Q4_K_M3.1 GB
ReasoningTool useVision
QW
Qwen3.8-27B
Qwen · gihakkk
Params27.3B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
QW
Qwen3 8B Abliterated
Qwen · 123lanhua
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
GE
gemma-4-E4B-it-heretic
Gemma · JMingo
Params7.46B
Context128K
Q4_K_M4.9 GB
CodingReasoningTool use
MU
Muse Glimmer 30B Heretic
Muse · cryptonaut
Params27.9B
Context128K
Q4_K_M17.3 GB
ReasoningTool useVision
QW
Qwen3.5-0.8B
Qwen · bubiche
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision

Other quants

Keep browsing