Q2_K_XL GGUF models
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 962 models have a Q2_K_XL file. Sizes run from 92M to 2780B parameters. The longest trained context is 10240K tokens.
QW
Qwen3.5-0.8B
Qwen · matthewj-t6
Params752M
Context256K
Q4_K_M0.5 GB
GE
gemma 4 26B A4B it DASHQ Q2
Gemma · jkim96
Params25.2B
Context256K
Smallest10.1 GB
GE
Gemma-3-4B-It
Gemma · sahadat369
Params3.88B
Context128K
Q4_K_M2.5 GB
DE
DeepSeek R1 BF16
DeepSeek · XythicK
Params671B
Context160K
Q4_K_M404.4 GB
QW
Qwen3.8 27b noslop
Qwen · RefinedNeuro
Params27.3B
Context256K
Q4_K_M16.8 GB
QW
Qwen2.5-Vl-7B-Instruct
Qwen · goushuai123
Params7.62B
Context125K
Q4_K_M4.7 GB
QW
Qwen3.5-9B
Qwen · Xlnk
Params8.95B
Context256K
Q4_K_M5.7 GB
QW
Qwen3.6-27B
Qwen · cmp-nct
Params26.9B
Context256K
Q4_K_M16.8 GB
SM
HuggingFaceTB_SmolLM3 3B
SmolLM · Alcoft
Params3.08B
Context64K
Q4_K_M1.9 GB
LL
Llama-3.2-1B-Instruct
Llama · RekcyDecky
Params1.24B
Context128K
Q4_K_M0.8 GB
QW
Qwen3-Coder-30B-A3B-Instruct
Qwen · cartoon45
Params30.5B
Context256K
Q4_K_M18.6 GB
GE
gemma-4-E2B-it-ultra-uncensored-heretic
Gemma · JMingo
Params4.63B
Context128K
Q4_K_M3.1 GB
EL
EleMo V2 Base
Elemo · Earlychildhoodeducation
Params27.3B
Context256K
Q4_K_M16.5 GB
QW
Qwen3.8-27B
Qwen · FenomAI
Params27.3B
Context256K
Q4_K_M17.1 GB
GL
GLM 5.2 ewaste edition
GLM · SixVolts
Params754B
Context1024K
Smallest243.6 GB
NE
OpenReasoning Nemotron 32B
Nemotron · jkim96
Params32.8B
Context128K
Smallest9.2 GB
MI
Mimo-Vl-7B-Rl
Mimo · akpsahan
Params7.62B
Context125K
Q4_K_M4.7 GB
QW
Qwen3.5-9B
Qwen · duolaf
Params8.95B
Context256K
Q4_K_M5.7 GB
GE
Gemma-3-27B-It
Gemma · tripolskypetr
Params27B
Context128K
Q4_K_M16.5 GB
DE
Huihui DeepSeek V4.1 Flash 1017 abliterated
DeepSeek · AshwinX
Params1.68B
Context1024K
Smallest0.6 GB
QW
Qwen3.8-27B
Qwen · bramburn
Params27.3B
Context256K
Q4_K_M16.6 GB
MI
Ministral 3 3B Instruct 2512 DASHQ Q2
Mistral · jkim96
Params3.43B
Context256K
Smallest1.1 GB
QW
Qwen3.8 27B Unleashed
Qwen · SwagMessiah100
Params26.9B
Context256K
Q4_K_M16.5 GB
QW
Qwen3-8B
Qwen · cmp-nct
Params8.19B
Context40K
Q4_K_M5.0 GB
QW
Qwen3.8-27B
Qwen · vs4vijay
Params27.3B
Context256K
Q4_K_M17.1 GB
DE
Huihui DeepSeek V4.1 Flash 1017 abliterated
DeepSeek · Ashwinxs
Params1.68B
Context1024K
Smallest0.6 GB
MI
Ministral 3 8B Instruct 2512 DASHQ Q2
Mistral · jkim96
Params8.49B
Context256K
Smallest2.6 GB
KI
Kimi-K2-Instruct
Kimi · jobs-git
Params1030B
Context128K
Q4_K_M620.8 GB
QW
Qwen3.6-35B-A3B
Qwen · opensota
Params34.7B
Context256K
Q4_K_M22.1 GB
ER
Ernie-4.5-21B-A3B-Thinking
Ernie · XythicK
Params21.8B
Context128K
Q4_K_M13.3 GB