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.
DO
Dots.Llm1.Inst
Dots · unsloth
Params143B
Context32K
Q4_K_M94.5 GB
QW
Qwen_Qwen3 4B Thinking 2507
Qwen · Alcoft
Params4B
Context256K
Q4_K_M2.4 GB
GP
Gpt-Oss-Safeguard-20B
gpt-oss · unsloth
Params20.9B
Context128K
Q4_K_M11.6 GB
FA
Falcon-H1-3B-Instruct
Falcon · unsloth
Params3.15B
Context128K
Q4_K_M1.9 GB
QW
Qwen2.5-Vl-7B-Instruct
Qwen · mnsims1024
Params7.62B
Context125K
Q4_K_M4.7 GB
QW
Qwen3-Vl-4B-Thinking-1M
Qwen · unsloth
Params4B
Context977K
Q4_K_M2.5 GB
QW
Qwen3.6-35B-A3B
Qwen · AtomicChat
Params447M
Context256K
Smallest17.7 GB
QW
Qwen3-Vl-30B-A3B-Thinking-1M
Qwen · unsloth
Params30.5B
Context977K
Q4_K_M18.6 GB
MI
Minimax H3 pruned
Minimax · PurpleBlazey
Params20.1B
Context256K
Smallest6.3 GB
QW
Qwen3-16B-A3B
Qwen · unsloth
Params16B
Context40K
Q4_K_M9.8 GB
QW
Qwen3.8-27B
Qwen · SeraphicHero
Params27.3B
Context256K
Q4_K_M16.5 GB
QW
Qwen3.8-27B
Qwen · Snowwhite00
Params27.3B
Context256K
Q4_K_M16.5 GB
MU
Muse Glimmer 30B Uncensored Heretic
Muse · OS-Software
Params27.9B
Context128K
Q4_K_M16.9 GB
GE
Gemma-4-26B-A4B-It-Ultra-Uncensored-Heretic
Gemma · JMingo
Params25.2B
Context256K
Q4_K_M16.9 GB
QW
UD 2.0 Qwen3.6 35B A3B Claude 4.6 Opus Reasoning Distilled
Qwen · mfielding92
Params34.7B
Context256K
Q4_K_M22.1 GB
NE
ThinkingCap Nemotron 3.5 Lightning 30B A3B abliterated
Nemotron · IstroSec
Params32.9B
Context1024K
Smallest0.1 GB
GE
gemma-4-31B-it-uncensored-heretic
Gemma · JMingo
Params30.7B
Context256K
Q4_K_M18.3 GB
QW
Qwen3.8 27B Heretic Dynamic
Qwen · ajgazin
Params27.3B
Context256K
Smallest17.6 GB
QW
Qwen3.5-4B
Qwen · Fix-AI
Params4.21B
Context256K
Q4_K_M2.7 GB
MI
Ministral 3 3B Instruct 2512
Mistral · EnlistedGhost
Params3.43B
Context256K
Smallest1.3 GB
GE
Gemma 4 12B It Qat
Gemma · dahara1
Params11.9B
Context256K
Q4_K_M7.1 GB
NE
NVIDIA-Nemotron-3.5-Bolt-74B-DERISKED
Nemotron · freakyskittle
Params74B
Context1024K
Q4_K_M46.4 GB
QW
JoyFox Reverie 27B
Qwen · joyfox
Params27.3B
Context256K
Q4_K_M16.5 GB
QW
Qwen3-32B
Qwen · openwalrus
Params32.8B
Context40K
Q4_K_M19.8 GB
QW
Qwen3-Vl-4B-Instruct-1M
Qwen · unsloth
Params4B
Context977K
Q4_K_M2.5 GB
QW
Qwen2.5 VL 7B Instruct
Qwen · ariel-pillar
Params7.62B
Context32K
Q4_K_M4.7 GB
OL
Olmo-3.1-32B-Think
OLMo · unsloth
Params32.2B
Context64K
Q4_K_M19.5 GB
MI
Mistral-Small-3.2-24B-Instruct-2506
Mistral · Sci-fi-vy
Params23.6B
Context128K
Q4_K_M14.3 GB
QW
Qwen3.6 35B A3B REAM 160 ru agent GGUF MTPLess
Qwen · WaveCut
Params22.6B
Context256K
Q4_K_M13.8 GB
QW
Qwen3-Vl-32B-Thinking
Qwen · unsloth
Params32.8B
Context256K
Q4_K_M19.8 GB