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.

Most downloadedNewestLargestLongest contextSmallest
MI
Ministral-3-14B-Instruct-2512
Mistral · iasarkar
Params13.5B
Context256K
Q4_K_M8.2 GB
Tool useVision
QW
Qwen3.8-27B
Qwen · FokusDK
Params27.3B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
OR
Tiel Coder 35B A3B GGUF MTP
Ornith · dotnfc
Params447M
Context256K
Smallest13.2 GB
CodingVision
VI
Vibethinker 1.5b Gguf_F16
Vibethinker · constructai
Params1.54B
Context128K
Q4_K_M1.0 GB
CodingReasoningTool use
QW
Qwen3.6-35B-A3B
Qwen · Distillio
Params34.7B
Context256K
Q4_K_M22.1 GB
ReasoningTool useVision
QW
Qwen3.6-27B
Qwen · tybuddy
Params27.3B
Context256K
Q4_K_M17.1 GB
ReasoningTool useVision
QW
Qwen3.5-9B
Qwen · Mer0vin8ian
Params8.95B
Context256K
Q4_K_M5.7 GB
ReasoningTool useVision
GE
Gemma-4-26B-A4B-It-Japanese
Gemma · JMingo
Params19.3B
Context256K
Q4_K_M13.1 GB
ReasoningTool use
QW
QwQ 32B DASHQ Q2
Qwen · jkim96
Params32.8B
Context40K
Smallest9.2 GB
ReasoningTool use
NE
Nvidia-Nemotron-3-Nano-Omni-30B-A3B-Reasoning
Nemotron · MuVeraAI
Params31.6B
Context1024K
Q4_K_M23.9 GB
ReasoningTool useVision
QW
Qwen3.6-27B
Qwen · kimzonick
Params27.3B
Context256K
Q4_K_M17.1 GB
ReasoningTool useVision
KI
Kimi-K2.7-Code
Kimi · eadx
Params1030B
Context256K
Smallest303.9 GB
CodingReasoningTool use
QW
Qwen3.6-35B-A3B
Qwen · poppingstar
Params35.5B
Context256K
Q4_K_M22.7 GB
ReasoningTool useVision
GE
Gemma-4-E4B-It
Gemma · ktruestory
Params7.52B
Context128K
Q4_K_M5.0 GB
ReasoningTool useVision
QW
Qwen3.8-27B
Qwen · adaliboy
Params27.3B
Context256K
Q4_K_M17.1 GB
ReasoningTool useVision
QW
Qwen3.5-9B
Qwen · DevinMox
Params8.95B
Context256K
Q4_K_M5.7 GB
ReasoningTool useVision
QW
Qwen3.5-0.8B
Qwen · ChuanShun
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
MI
Ministral 3 8B Reasoning 2512 DASHQ Q2
Mistral · jkim96
Params8.49B
Context256K
Smallest2.6 GB
ReasoningTool use
QW
Qwen3.5-0.8B
Qwen · oki602960
Params773M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
GE
Gemma-4-E2B-It
Gemma · fridaycandour
Params4.65B
Context128K
Q4_K_M3.1 GB
ReasoningTool useVision
QW
Qwen3-4B-Instruct-2507
Qwen · Khawarr
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
GE
Gemma-4-31B-It
Gemma · fractaldactal
Params30.7B
Context256K
Q4_K_M18.3 GB
ReasoningTool useVision
QW
Qwen3.5-27B
Qwen · duolaf
Params26.9B
Context256K
Q4_K_M16.7 GB
ReasoningTool useVision
PH
Phi 4 reasoning plus DASHQ Q2
Phi · jkim96
Params14.7B
Context32K
Smallest4.2 GB
Reasoning
QW
Qwen3.6-35B-A3B
Qwen · djikon
Params35.5B
Context256K
Q4_K_M22.7 GB
ReasoningTool useVision
DE
Huihui DeepSeek V4.1 Flash 1017 abliterated
DeepSeek · Mattobik
Params1.68B
Context1024K
Smallest0.6 GB
GGUF
MI
Ministral 3 3B Reasoning 2512 DASHQ Q2
Mistral · jkim96
Params3.43B
Context256K
Smallest1.1 GB
ReasoningTool use
GE
Gemma-4-12B-It
Gemma · eadx
Params11.9B
Context128K
Q4_K_M7.1 GB
ReasoningTool useVision
GE
Gemma-4-26B-A4B-It
Gemma · ipsarkar
Params25.2B
Context256K
Q4_K_M16.9 GB
ReasoningTool useVision
QW
Qwen3.5-0.8B
Qwen · Zombe123
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision

Other quants

Keep browsing