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.
MI
Mistral-Small-4-119B-2603
Mistral · stefan-terdell-cleura
Params119B
Context1024K
Q4_K_M73.7 GB
OP
OpenCrystal 15B L3 v2
Opencrystal · bartowski
Params15B
Context8K
Q4_K_M9.1 GB
QW
Qwen3.8-27B
Qwen · AGW06
Params27.3B
Context256K
Q4_K_M16.5 GB
QW
Qwen3.5-9B
Qwen · seerware
Params8.95B
Context256K
Q4_K_M5.7 GB
QW
Qwen3.5-4B
Qwen · ente-ai
Params4.21B
Context256K
Q4_K_M2.7 GB
FA
Fara 7B
Fara · XythicK
Params7.62B
Context125K
Q4_K_M4.7 GB
AR
Arcee Scribe
Arcee · arcee-ai
Params7.74B
Context32K
Q4_K_M4.7 GB
LL
Reflection Llama 3.1 70B
Llama · osanseviero
Params70.6B
Context8K
Q4_K_M42.5 GB
OR
Tiel Coder 35B A3B
Ornith · npario
Params34.7B
Context256K
Smallest0.2 GB
LL
Llama-3-Perky-Pat-Instruct-8B
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
QW
Qwen3.6-35B-A3B
Qwen · AstroJes
Params35.5B
Context256K
Q4_K_M22.7 GB
BE
Behemoth 123B v1.2
Behemoth · bartowski
Params123B
Context128K
Q4_K_M73.2 GB
QW
Qwen3.8-27B
Qwen · N8STORM
Params27.3B
Context256K
Q4_K_M16.5 GB
GL
Glm-4.7-Flash
GLM · tripolskypetr
Params29.9B
Context198K
Q4_K_M18.3 GB
QW
QwQ 32B Preview abliterated
Qwen · Iambackup
Params32B
Context—
Q4_K_M19.9 GB
LL
Halu 8B Llama3 Blackroot
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
QW
Qwen3.5-4B
Qwen · hikka2515
Params4.33B
Context256K
Q4_K_M2.8 GB
AR
Arcee Maestro 7B Preview
Arcee · arcee-ai
Params7.61B
Context128K
Q4_K_M4.7 GB
QW
Qwen3.5-4B
Qwen · bubiche
Params4.21B
Context256K
Q4_K_M2.7 GB
MA
Mai-Ds-R1
Mai · unsloth
Params671B
Context160K
Q4_K_M404.7 GB
QW
Qwen2.5 32B AGI
Qwen · williamchangtw
Params32.8B
Context32K
Q4_K_M19.9 GB
FA
Fara 7B
Fara · AlexKitipov
Params7.62B
Context125K
Q4_K_M4.7 GB
MI
Dolphin Mistral 24B Venice Edition
Mistral · Yixman
Params23.6B
Context32K
Q4_K_M14.3 GB
MO
Monstral 123B
Monstral · bartowski
Params123B
Context128K
Q4_K_M73.2 GB
QW
Qwen3.6-35B-A3B
Qwen · developerjeremylive
Params35.5B
Context256K
Q4_K_M22.7 GB
QW
Qwen3.6 35B A3B REAM 160 ru agent GGUF MTPLess
Qwen · BahamutRU
Params35B
Context—
Q4_K_M13.8 GB
QW
Virtuoso Small
Qwen · arcee-ai
Params14.8B
Context128K
Q4_K_M9.0 GB
JA
AI21 Jamba Large 1.7
Jamba · bartowski
Params399B
Context256K
Q4_K_M240.4 GB
QW
Qwen3.8 Flash Next
Qwen · AnonimousA
Params117B
Context256K
Smallest61.9 GB
LL
llama-3-meerkat-8b-v1.0
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB