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.
GE
Gemma-4-31B-It
Gemma · 888rok
Params30.7B
Context256K
Smallest15.4 GB
LI
Ling Mini 2.0
Ling · Manojb
Params16.3B
Context32K
Smallest8.1 GB
OL
OLMoE 1B 7B 0924 Instruct
OLMo · mitulagr2
Params6.92B
Context4K
Smallest3.7 GB
QW
Qwen3.5 27B
Qwen · Manojb
Params26.9B
Context256K
Smallest15.7 GB
OL
OLMoE 1B 7B 0924 Instruct
OLMo · Felladrin
Params6.92B
Context4K
Smallest3.7 GB
QW
Qwen3.5-35B-A3B
Qwen · 888rok
Params34.7B
Context256K
Smallest16.6 GB
QW
posit ds
Qwen · dpletta
Params30.5B
Context256K
Smallest13.8 GB
QW
Qwen Image 2.1 Turbo
Qwen · aivideo4k
Params7.12B
Context—
Q4_K_M4.2 GB
QW
backup 2026 09 08 Qwen3.8 27B Unleashed SSMFIX
Qwen · burningfeet
Params27.3B
Context256K
Q4_K_M16.5 GB
IC
ICONNAI ICONN 1
Iconnai · bartowski
Params84B
Context32K
Q4_K_M50.9 GB
MI
MiniMax M2.5 PRISM PRO
Minimax · Ex0bit
Params229B
Context192K
Smallest60.3 GB
QW
obliteratus dual model chatbot
Qwen · mido09
Params8.95B
Context256K
Q4_K_M5.7 GB
QW
Qwen2.5 Coder 32B Instruct
Qwen · Bosswinner
Params32.8B
Context32K
Q4_K_M19.9 GB
IN
inkling
Inkling · zurichquant
Params947B
Context1024K
Smallest270.2 GB
QW
2026 08 25 . unsloth . Qwen3.8 27B
Qwen · burningfeet
Params27.3B
Context256K
Q4_K_M16.5 GB
QW
Qwen3.8 27B
Qwen · DollasAndSpence
Params27.3B
Context256K
Q4_K_M16.5 GB
QW
Qwen3 Coder 30B A3B Instruct
Qwen · balajiduraisamy
Params30.5B
Context256K
Q4_K_M18.6 GB
LL
Llama 3.2 3B Instruct
Llama · balajiduraisamy
Params3.21B
Context128K
Q4_K_M2.0 GB
LL
Meta Llama 3.1 8B Instruct
Llama · balajiduraisamy
Params8.03B
Context128K
Q4_K_M4.9 GB
GL
GLM 5.3 DERISKED UD Q3 K XL
GLM · defiobi00
Params754B
Context1024K
Smallest343.0 GB