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.
MI
Ministral-3-3B-Reasoning-2512
Mistral · unsloth
Params3.43B
Context256K
Q4_K_M2.1 GB
HY
Hy-Mt2-7B
unsloth
Params7.5B
Context256K
Q4_K_M4.6 GB
QW
Qwen3-Coder-30B-A3B-Instruct-1M
Qwen · unsloth
Params30.5B
Context1024K
Q4_K_M18.6 GB
OR
Ornith 1.0 35B
Ornith · unsloth
Params34.7B
Context256K
Q4_K_M22.1 GB
ST
Step-3.7-Flash
Step · unsloth
Params197B
Context256K
Q4_K_M122.1 GB
QW
Qwen3-235B-A22B
Qwen · unsloth
Params235B
Context40K
Q4_K_M142.2 GB
MI
Mistral-Medium-3.5-128B
Mistral · unsloth
Params125B
Context256K
Q4_K_M74.9 GB
MI
Devstral-Small-2507
Mistral · unsloth
Params23.6B
Context128K
Q4_K_M14.3 GB
PH
Phi-4-Mini-Reasoning
Phi · unsloth
Params3.84B
Context128K
Q4_K_M2.5 GB
QW
Qwen3-Vl-2B-Thinking
Qwen · unsloth
Params1.72B
Context256K
Q4_K_M1.1 GB
MI
Minimax-M3
Minimax · unsloth
Params426B
Context1024K
Q4_K_M264.9 GB
QW
Qwen3-235B-A22B-Instruct-2507
Qwen · unsloth
Params235B
Context256K
Q4_K_M142.2 GB
GL
GLM 5
GLM · unsloth
Params754B
Context198K
Q4_K_M455.9 GB
GL
Glm-4-9B-0414
GLM · unsloth
Params9.4B
Context32K
Q4_K_M6.2 GB
MI
Ministral-3-14B-Reasoning-2512
Mistral · unsloth
Params13.5B
Context256K
Q4_K_M8.2 GB
QW
Qwen3-Coder-480B-A35B-Instruct
Qwen · unsloth
Params480B
Context256K
Q4_K_M290.1 GB
NE
Nvidia-Nemotron-3-Super-120B-A12B
Nemotron · unsloth
Params121B
Context1024K
Q4_K_M82.5 GB
GL
Glm-4-32B-0414
GLM · unsloth
Params32.6B
Context32K
Q4_K_M19.7 GB
PH
Phi-4-Reasoning-Plus
Phi · unsloth
Params14.7B
Context32K
Q4_K_M9.1 GB
OR
Orpheus-3B-0.1-Ft
Orpheus · unsloth
Params3.3B
Context128K
Q4_K_M2.1 GB
GL
Glm-Z1-9B-0414
GLM · unsloth
Params9.4B
Context32K
Q4_K_M6.2 GB
NE
Nvidia-Nemotron-3-Nano-4B
Nemotron · unsloth
Params3.97B
Context1024K
Q4_K_M2.9 GB
GL
GLM 4.6
GLM · unsloth
Params357B
Context198K
Q4_K_M215.6 GB
MI
Minimax-M2
Minimax · unsloth
Params230B
Context192K
Q4_K_M138.3 GB
QW
Qwen3-Vl-8B-Thinking
Qwen · unsloth
Params8.19B
Context256K
Q4_K_M5.0 GB
FU
Functiongemma-270M-It
Functiongemma · unsloth
Params268M
Context32K
Q4_K_M0.3 GB
HE
Hermes-4-70B
Hermes · unsloth
Params70.6B
Context128K
Q4_K_M42.5 GB
AP
Apertus-8B-Instruct-2509
Apertus · unsloth
Params8.05B
Context64K
Q4_K_M5.1 GB
QW
Qwen3-Vl-235B-A22B-Instruct
Qwen · unsloth
Params235B
Context256K
Q4_K_M142.2 GB
QW
Qwen3-Vl-4B-Thinking
Qwen · unsloth
Params4B
Context256K
Q4_K_M2.5 GB