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
GE
Gemma-4-E4B-It
Gemma · Arabic250
Params7.52B
Context128K
Q4_K_M5.0 GB
ReasoningTool useVision
GL
GLM 5.3 Flash
GLM · Nil626yhh
Params321B
Context1024K
Smallest93.1 GB
ReasoningTool useVision
QW
Qwen3.5-9B
Qwen · bogservi
Params8.95B
Context256K
Q4_K_M5.7 GB
ReasoningTool useVision
GL
GLM 5.3 Flash
GLM · ashuaria
Params321B
Context1024K
Smallest93.1 GB
ReasoningTool useVision
OR
Ornith 1.0 35B
Ornith · Hagwell
Params34.7B
Context256K
Q4_K_M22.1 GB
ReasoningTool useVision
LL
Llama-3-8B-Stroganoff
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Qwen3.5-4B
Qwen · MdSajjadurRahaman
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
QW
Qwen3.5-4B
Qwen · Vocabook
Params4.21B
Context256K
Smallest2.4 GB
ReasoningTool useVision
NO
North Mini Code 1.0 Uncensored Heretic
North · OS-Software
Params30.5B
Context488K
Smallest14.3 GB
CodingReasoningTool use
GE
Gemma-4-E4B-It
Gemma · qiufeng001
Params7.52B
Context128K
Q4_K_M5.0 GB
ReasoningTool useVision
GL
GLM 4.5 Air Derestricted
GLM · TMNE
Params110B
Context128K
Q4_K_M73.5 GB
ReasoningTool use
QW
Qwen3.5-4B
Qwen · nutyon1
Params4.33B
Context256K
Q4_K_M2.8 GB
ReasoningTool useVision
QW
Qwen3 Next REAP 15B A3B Thinking
Qwen · lovedheart
Params16.8B
Context256K
Smallest11.7 GB
ReasoningTool use
GE
Gemma 4 E4B It
Gemma · Capsulanet
Params7.52B
Context128K
Q4_K_M5.4 GB
ReasoningTool useVision
GE
gen myanmar 4 E2B
Gemma · BaybeDragon
Params4.65B
Context128K
Q4_K_M3.1 GB
ReasoningTool useVision
QW
Qwen3.5-4B
Qwen · dev-vinod
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
GE
Gemma-4-12B-It
Gemma · vickersdp
Params11.9B
Context256K
Q4_K_M7.1 GB
ReasoningTool useVision
SM
SmolLM2 1.7B Instruct
SmolLM · aa1602295777
Params1.71B
Context8K
Q4_K_M1.1 GB
GGUF
QW
Qwen3.6 27B abliterated v2
Qwen · groxaxo
Params26.9B
Context256K
Smallest11.4 GB
ReasoningTool use
DE
DeepSeek V4 Flash 0731
DeepSeek · Nil626yhh
Params284B
Context1024K
Smallest10.9 GB
GGUF
NE
NemoMix Unleashed 12B
Nemomix · violetahayashi69
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
GL
GLM 5.3 Flash
GLM · zurichquants
Params321B
Context1024K
Smallest93.1 GB
ReasoningTool useVision
QW
Qwen3 72B Embiggened
Qwen · Ailearner007
Params72.7B
Context40K
Q4_K_M47.4 GB
ReasoningTool use
DE
Deepseek-V4-Flash
DeepSeek · poppingstar
Params284B
Context1024K
Smallest82.5 GB
ReasoningTool use
QW
Qwen3.6 27B Omnimerge v4
Qwen · fribourgquant
Params26.9B
Context256K
Q4_K_M16.5 GB
CodingReasoningTool use
LL
Llama 3.2 3B Instruct
Llama · benniekiss
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
GL
compressed backup GLM 5.2
GLM · vinayakkamboj
Params754B
Context1024K
Q4_K_M465.8 GB
ReasoningTool use
GE
Gemma-4-E2B-It
Gemma · 0x3
Params4.65B
Context128K
Q4_K_M3.1 GB
ReasoningTool useVision
QW
Qwen3.8-27B
Qwen · 2531oupp
Params27.3B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
QW
vai 8b
Qwen · votal-ai
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use

Other quants

Keep browsing