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
QW
Qwerus 7B
Qwerus · bartowski
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
QW
Qwen2.5-Vl-7B-Instruct
Qwen · divyanshugaur
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
QW
Qwen3.8-27B
Qwen · Hagwell
Params27.3B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
GR
GRMR 2B Instruct
Grmr · bartowski
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
LL
Hermes-2-Theta-Llama-3-70B
Llama · bartowski
Params70.6B
Context8K
Q4_K_M42.5 GB
Tool use
CA
Captain_BMO 12B
Captain · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
GE
Gemma-3-1B-It
Gemma · stratalab-org
Params1B
Context32K
Q4_K_M0.8 GB
GGUF
OR
Ornith 1.5 397B GGUF imatrix
Ornith · cdanis
Params403B
Context256K
Smallest1.1 GB
GGUF
CA
arcee ai Caller
Caller · bartowski
Params32.8B
Context32K
Q4_K_M19.9 GB
GGUF
R1
R1 1776
unsloth
Params671B
Context160K
Q4_K_M404.4 GB
CodingReasoningTool use
QW
Nodmix3.6 35B A3B
Qwen · Nodmix
Params34.7B
Context256K
Q4_K_M22.1 GB
ReasoningTool useVision
BI
BigQwen2.5 125B Instruct
Bigqwen · bartowski
Params125B
Context32K
Q4_K_M81.6 GB
Tool use
ER
Ernie-4.5-300B-A47B-Pt
Ernie · unsloth
Params299B
Context128K
Q4_K_M180.2 GB
GGUF
MI
Mahou 1.5 mistral nemo 12B
Mistral · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
QW
axelle
Qwen · arvvvvvv
Params34.7B
Context256K
Q4_K_M22.0 GB
ReasoningTool useVision
GE
Huihui Gemma 4 26B A4B It Abliterated
Gemma · deewu0809
Params25.2B
Context256K
Q4_K_M16.9 GB
ReasoningTool useVision
QW
Qwen3-Coder-30B-A3B-Instruct
Qwen · brodatech
Params30.5B
Context256K
Q4_K_M18.6 GB
CodingTool use
OL
OLMoE 1B 7B 0924 Instruct
OLMo · armandosds
Params6.92B
Context4K
Q4_K_M4.2 GB
GGUF
GE
Gemma-3-12B-It
Gemma · socrate-tech
Params11.8B
Context128K
Q4_K_M7.3 GB
Vision
CO
Confucius O1 14B
Confucius · bartowski
Params14.8B
Context32K
Q4_K_M9.0 GB
Tool use
QW
Qwen3-Coder-30B-A3B-Instruct
Qwen · Quixote12
Params30.5B
Context256K
Q4_K_M18.6 GB
CodingTool use
QW
Qwen2.5 3B
Qwen · EasierAI
Params3.09B
Context32K
Q4_K_M1.9 GB
GGUF
AN
G3 27B Animus V12.0 Redux
Animus · bartowski
Params27B
Context128K
Q4_K_M16.5 GB
RoleplayVision
TH
L3.1 TheGreenLion 8b SFT v0.1.2
Thegreenlion · bartowski
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
TW
TwinLlama 3.1 8B 2
Twinllama · bartowski
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
TR
Triplex
Triplex · bartowski
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
CA
Captain BMO 0.420 Magnum 12B
Captain · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
LL
Llama3 Crab SFT
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LY
Lyra Gutenbergs Twilight Magnum 12B
Lyra · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
GE
Gemma-4-E2B-It
Gemma · aoiandroid
Params4.65B
Context128K
Q4_K_M3.1 GB
ReasoningTool useVision

Other quants

Keep browsing