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
Qwen3.5-4B
Qwen · harsha-math
Params4.21B
Context256K
Q4_K_M2.7 GB
DE
DeepSeek V4 Flash 0731
DeepSeek · speakguru
Params284B
Context1024K
Smallest10.9 GB
GE
Gemma-4-E2B-It
Gemma · heyAadi
Params4.65B
Context128K
Q4_K_M3.1 GB
GE
Gemma-4-E2B-It
Gemma · redmik60
Params4.65B
Context128K
Q4_K_M3.1 GB
GE
Gemma-4-E4B-It
Gemma · manojbillionaire123
Params7.52B
Context128K
Q4_K_M5.0 GB
LL
Hyze1BInstruct
Llama · HyzeAI
Params1.24B
Context128K
Q4_K_M0.8 GB
QW
Qwen3.5-9B
Qwen · Manojb
Params8.95B
Context256K
Smallest5.1 GB
GE
Gemma-4-E2B-It
Gemma · gijl
Params4.65B
Context128K
Q4_K_M3.1 GB
DE
DeepSeek V4 Flash 0731
DeepSeek · Stk88
Params284B
Context1024K
Smallest10.9 GB
QW
Qwen3.5-4B
Qwen · Felladrin
Params4.21B
Context256K
Smallest2.4 GB
DE
DeepSeek V4 Flash 0731
DeepSeek · lyssquant
Params284B
Context1024K
Smallest10.9 GB
GE
Neve Cascade 3 1B
Gemma · NeveAI
Params1B
Context32K
Smallest0.7 GB
LF
LFM2.5 2.6B
Lfm · kelvinlamptey
Params2.7B
Context125K
Q4_K_M1.7 GB
ET
ML MS Etheris 123B
Etheris · bartowski
Params123B
Context32K
Q4_K_M73.2 GB
QW
Qwen3.5-0.8B
Qwen · votal-ai
Params752M
Context256K
Q4_K_M0.5 GB
QW
Qwen3.5-0.8B
Qwen · BiAffect
Params752M
Context256K
Q4_K_M0.5 GB
GE
Gemma-4-31B-It
Gemma · glymm
Params30.7B
Context256K
Q4_K_M18.3 GB
QW
Qwen3.5-9B
Qwen · Viral2AI
Params8.95B
Context256K
Q4_K_M5.7 GB
QW
Qwen3.6 REAP
Qwen · JZC973
Params25.7B
Context256K
Smallest10.5 GB
CR
CREC N WREC Mate 24B v2
Crec · Casual-Autopsy
Params23.6B
Context32K
Q4_K_M14.3 GB
GE
Gemma-4-26B-A4B-It-Japanese
Gemma · JMingo
Params13.2B
Context256K
Q4_K_M9.1 GB
GE
Gemma-4-E2B-It
Gemma · dudeidkwhattodo
Params4.65B
Context128K
Q4_K_M3.1 GB
GE
Gemma-4-E2B-It
Gemma · manojbillionaire123
Params4.65B
Context128K
Q4_K_M3.1 GB
GE
Gemma-4-E4B-It
Gemma · gijl
Params7.52B
Context128K
Q4_K_M5.0 GB
FA
gguf Q3 K XL falcon mamba 7b
Falcon · Felladrin
Params7.27B
Context1024K
Smallest3.5 GB
QW
Qwen3.6-27B
Qwen · orion-labs
Params26.9B
Context256K
Q4_K_M16.8 GB
DE
DeepSeek V4 Flash 0731
DeepSeek · glxiexie
Params284B
Context1024K
Smallest10.9 GB
LL
Llama 3.2 1B Instruct
Llama · asad959191
Params1.24B
Context128K
Q4_K_M0.8 GB
QW
Qwen3.5 122B A10B Heretic
Qwen · SassyDiffusion
Params122B
Context256K
Smallest41.8 GB
QW
Qwen3.6-27B
Qwen · poppingstar
Params27.3B
Context256K
Q4_K_M17.1 GB