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.
QW
Qwen3-0.6B
Qwen · Jeney
Params596M
Context40K
Q4_K_M0.4 GB
FA
Falcon3 7B Base
Falcon · bartowski
Params7.46B
Context32K
Q4_K_M4.6 GB
LL
CSM 1.0
Llama · lkl387
Params8.03B
Context128K
Q4_K_M4.9 GB
QW
Qwen3.5-35B-A3B
Qwen · l27335over
Params34.7B
Context256K
Q4_K_M22.0 GB
GE
gemma-4-E4B-it-uncensored-heretic
Gemma · JMingo
Params7.46B
Context128K
Q4_K_M4.9 GB
QW
Qwen3.6-27B
Qwen · Distillio
Params26.9B
Context256K
Q4_K_M16.8 GB
MA
Mag Mell Reasoner 12B
Mag · EnlistedGhost
Params12.2B
Context1000K
Q4_K_M7.7 GB
QW
Qwen3-8B
Qwen · openwalrus
Params8.19B
Context40K
Q4_K_M5.0 GB
LL
Tess 3 Llama 3.1 405B
Llama · bartowski
Params410B
Context128K
Q4_K_M245.7 GB
QW
Qwen3.8-27B
Qwen · ariel-pillar
Params27.3B
Context256K
Q4_K_M16.5 GB
HE
Hermes-4-70B
Hermes · genevaquant
Params70.6B
Context128K
Q4_K_M42.5 GB
QW
Qwen3.8-27B
Qwen · FreeMangione221
Params27.3B
Context256K
Q4_K_M16.5 GB
LL
EVA LLaMA 3.33 70B v0.0
Llama · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
LL
Llama 3.1 70B ArliAI RPMax v1.1
Llama · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
QW
Qwen3-14B
Qwen · openwalrus
Params14.8B
Context40K
Q4_K_M9.0 GB
QW
InfiniAILab QwQ 0.5B
Qwen · bartowski
Params494M
Context32K
Q4_K_M0.4 GB
QW
Qwen2.5-Omni-7B
Qwen · Kjppmp
Params7.62B
Context32K
Q4_K_M4.7 GB
GE
Gemma 4 E4B It
Gemma · indiansatoshi
Params7.52B
Context128K
Q4_K_M5.4 GB
QW
Qwen3.8-27B
Qwen · CrossNow
Params27.3B
Context256K
Q4_K_M17.1 GB
PN
L3 Pneuma 8B
Pneuma · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GE
Gemma-4-12B-It
Gemma · developerjeremylive
Params11.9B
Context256K
Q4_K_M7.1 GB
MI
Mistral Small 22B ArliAI RPMax v1.1
Mistral · dan517
Params22.2B
Context32K
Q4_K_M13.3 GB
QW
Qwen3.6 35B A3B REAM 160 ru agent
Qwen · BahamutRU
Params35B
Context—
Q4_K_M14.4 GB
LU
L3 Luna 8B
Luna · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
QW
Qwen3.5-0.8B
Qwen · axana-labs
Params752M
Context256K
Q4_K_M0.5 GB
QW
Qwen3-Vl-4B-Thinking
Qwen · cccccccccc418
Params4.02B
Context256K
Q4_K_M2.5 GB
LF
LFM2 2.6B Exp
Lfm · bartowski
Params2.7B
Context125K
Q4_K_M1.6 GB
MU
Muse Glimmer 30B
Muse · Distillio
Params27.9B
Context128K
Q4_K_M17.3 GB
NO
Nova Tempus 70B v0.1
Nova · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
QW
Qwen3.6-27B
Qwen · claymorecrystal
Params26.9B
Context256K
Q4_K_M16.8 GB