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.

Most downloadedNewestLargestLongest contextSmallest
DE
Deepseek-R1-Distill-Qwen-1.5B
DeepSeek · 39mk39mk
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
QW
Qwen3.5-0.8B
Qwen · ensu-app
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
LL
Hercules 6.0 Llama 3.1 8B
Llama · bartowski
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
MI
Voxtral Small 24B 2507
Mistral · Abu-Dju
Params23.6B
Context128K
Q4_K_M14.3 GB
Tool useVision
GE
Gemma-4-31B-It
Gemma · Lucerneallan
Params30.7B
Context256K
Q4_K_M18.3 GB
ReasoningTool useVision
GE
Gemma 4 E4B It
Gemma · recursechat
Params7.52B
Context128K
Q4_K_M5.4 GB
ReasoningTool useVision
CE
Celeste 12B V1.6
Celeste · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
FU
Functiongemma-270M-It
Functiongemma · ajmcclary
Params268M
Context32K
Q4_K_M0.3 GB
Tool use
GE
Gemma-4-E4B-It
Gemma · Jhhjjjjj
Params7.52B
Context128K
Q4_K_M5.0 GB
ReasoningTool useVision
QW
Qwen3.6-27B
Qwen · Distillio
Params27.3B
Context256K
Q4_K_M17.1 GB
ReasoningTool useVision
GL
GLM 5.3 Flash
GLM · CoboSan
Params321B
Context1024K
Smallest93.1 GB
ReasoningTool useVision
GE
Gemma-4-26B-A4B-It
Gemma · rahul-shukla
Params25.2B
Context256K
Q4_K_M16.9 GB
ReasoningTool useVision
QW
BigBubba Qwen3.6 27B
Qwen · Guile
Params27.3B
Context256K
Q4_K_M17.8 GB
ReasoningTool useVision
GE
Gemma-3N-E2B-It
Gemma · tripolskypetr
Params4.46B
Context32K
Q4_K_M2.8 GB
Vision
AR
Arco Put 6
Arco · bartowski
Params514M
Context8K
Q4_K_M0.3 GB
GGUF
MA
Magidonia 24B v4.3
Magidonia · Mrd1011
Params23.6B
Context128K
Q4_K_M14.3 GB
Tool use
QW
Qwen3.5 4B QD
Qwen · QuaduxIT
Params4.33B
Context256K
Smallest2.1 GB
ReasoningTool useVision
GE
Gemma-4-E2B-It-Japanese
Gemma · JMingo
Params2.34B
Context128K
Q4_K_M1.6 GB
ReasoningTool use
LL
Llama-3.2-3B-Instruct
Llama · goingmerry91
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
QW
Qwen3.6-35B-A3B
Qwen · Fastiraz
Params34.7B
Context256K
Q4_K_M22.1 GB
ReasoningTool useVision
RH
L3 Rhaenys 8B
Rhaenys · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
Roleplay
TQ
Tqwendo 36b
Tqwendo · bartowski
Params35.7B
Context32K
Q4_K_M21.6 GB
CodingTool use
QW
Qwen3 Coder 30B A3B Instruct 480B Distill V2 Fp32
Qwen · rodrigomt
Params30.5B
Context256K
Smallest13.8 GB
CodingTool use
LL
Llama-3.1-8B-Instruct
Llama · mohammedqarnuon
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
GL
GLM 5.3 Flash
GLM · lazywold
Params321B
Context1024K
Smallest93.1 GB
ReasoningTool useVision
DE
Deepseek-R1-Distill-Llama-8B
DeepSeek · recursechat
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
ER
Ernie-4.5-0.3B-Pt
Ernie · Dc15er
Params361M
Context128K
Q4_K_M0.2 GB
GGUF
QW
Qwen3.6 27B Omnimerge v4
Qwen · shaffhausen
Params26.9B
Context256K
Q4_K_M16.5 GB
CodingReasoningTool use
GE
Gemma 4 E2B It
Gemma · Capsulanet
Params4.65B
Context128K
Q4_K_M3.5 GB
ReasoningTool useVision
LL
Llama 3.2 1B Instruct
Llama · sir0min
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use

Other quants

Keep browsing