Q4_K_XL GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 1216 models have a Q4_K_XL file. Sizes run from 1M to 2780B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
OR
Ornith 35B
Ornith · AtomicChat
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
SP
Spark X2.6 4B SQL Cypher Agent
Spark · trjxter
Params4.11B
Context1024K
Q4_K_M2.6 GB
ReasoningTool use
QW
Qwen3.8-27B
Qwen · 1bit-MONSTER
Params27.3B
Context256K
Smallest1.4 GB
ReasoningTool use
QW
Qwen3.6-27B
Qwen · Ankushbl6
Params26.9B
Context256K
Q4_K_M16.8 GB
ReasoningTool useVision
GE
Gemma-4-E2B-It
Gemma · bubiche
Params4.65B
Context128K
Q4_K_M3.1 GB
ReasoningTool useVision
MI
Minimax-M3
Minimax · reduxv1
Params426B
Context1024K
Q4_K_M264.0 GB
ReasoningTool useVision
KI
Kimi-K2.7-Code
Kimi · Edmon02
Params1030B
Context256K
Smallest583.7 GB
CodingReasoningTool use
GE
Gemma 4 E2B it qat abliterated UD Q4 K XL
Gemma · RemySkye
Params4.63B
Context128K
Smallest2.6 GB
ReasoningTool useVision
GE
Gemma 4 31B StyleTune
Gemma · dexgeh
Params32.1B
Context256K
Smallest20.1 GB
ReasoningTool use
GP
Gpt-Oss-120B
gpt-oss · tripolskypetr
Params117B
Context128K
Q4_K_M62.8 GB
Tool use
GE
Gemma-4-E2B-It
Gemma · ALexJM19
Params4.65B
Context128K
Q4_K_M3.1 GB
ReasoningTool useVision
QW
Qwen3.5-9B
Qwen · Interlinkarts
Params8.95B
Context256K
Q4_K_M5.7 GB
ReasoningTool useVision
QW
Qwen3.5-122B-A10B
Qwen · tybuddy
Params122B
Context256K
Q4_K_M74.3 GB
ReasoningTool useVision
GE
Gemma-4-31B-It
Gemma · ipsarkar
Params30.7B
Context256K
Q4_K_M18.3 GB
ReasoningTool useVision
GL
GLM 5.3
GLM · Coder40-95
Params754B
Context1024K
Smallest216.7 GB
CodingReasoningTool use
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
GP
Gpt-Oss-20B
gpt-oss · tripolskypetr
Params20.9B
Context128K
Q4_K_M11.6 GB
Tool use
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
Qwen3.6-35B-A3B-QD
Qwen · QuaduxIT
Params35.5B
Context256K
Smallest10.6 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
QW
Qwen3.5-9B
Qwen · AaryanK
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
GE
gemma 4 31B it Q4 K local Q6 K global
Gemma · DZgas
Params30.7B
Context128K
Smallest0.3 GB
Vision
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

Other quants

Keep browsing