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
TO
totem slm rl v6
Totem · giocorte
Params4.02B
Context40K
Smallest2.6 GB
ReasoningTool use
WE
WEBGEN 4B Preview 480B Double Distill FP32
Webgen · rodrigomt
Params4.02B
Context256K
Smallest2.5 GB
GGUF
DE
DeepSeek V4 Flash 0731
DeepSeek · glxiexie
Params284B
Context1024K
Smallest10.9 GB
GGUF
QW
Qwen3.5-9B
Qwen · XpressAI
Params9.82B
Context256K
Smallest6.0 GB
ReasoningTool use
SM
smarter library models
Smarter · smartertechnologist
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
GE
Neve Echo 6 12B QAT
Gemma · NeveAI
Params11.9B
Context256K
Smallest6.7 GB
ReasoningTool useVision
QW
Qwen3.5 122B A10B Heretic
Qwen · SassyDiffusion
Params122B
Context256K
Smallest41.8 GB
ReasoningTool useVision
GE
kuza gemma 4 e2b
Gemma · kuzaai
Params4.63B
Context128K
Q4_K_M2.6 GB
Reasoning
NE
Nvidia-Nemotron-3-Super-120B-A12B
Nemotron · meshllm
Params124B
Context1024K
Smallest89.7 GB
ReasoningTool use
QW
Qwen3-235B-A22B-Instruct-2507
Qwen · moxin-org
Params235B
Context256K
Smallest89.0 GB
ReasoningTool use
QW
Qwen3.6-27B
Qwen · beclab
Params27.3B
Context256K
Smallest15.7 GB
ReasoningTool useVision
QW
Qwen3.6-27B
Qwen · poppingstar
Params27.3B
Context256K
Q4_K_M17.1 GB
ReasoningTool useVision
DE
Deepseek-V4-Flash
DeepSeek · tHEsadad
Params284B
Context1024K
Smallest82.5 GB
ReasoningTool use
QW
Qwen3.5-122B-A10B-abliterix
Qwen · groxaxo
Params122B
Context256K
Smallest76.9 GB
ReasoningTool use
QW
Neve Strata S3 9B MTP
Qwen · NeveAI
Params9.2B
Context256K
Smallest6.1 GB
ReasoningTool useVision
IN
TML Inkling
Inkling · Pq234
Params947B
Context1024K
Smallest270.2 GB
ReasoningTool useVision
GE
Gemma-4-E4B-It
Gemma · BlacknodeLTDAI
Params7.52B
Context128K
Smallest5.1 GB
ReasoningTool use
GE
Gemma-4-26B-A4B-It
Gemma · mangaba-ai
Params25.2B
Context256K
Smallest17.0 GB
ReasoningTool use
GE
kuza gemma 4 e2b old
Gemma · kuzaai
Params4.63B
Context128K
Q4_K_M2.6 GB
Reasoning
TI
Tinfield 1 Q4 K XL
Tinfield · badtheorylabs
Params177B
Context256K
Smallest111.3 GB
ReasoningTool use
GE
Gemma-4-E4B-It
Gemma · SciTools
Params11.9B
Context128K
Q4_K_M5.0 GB
ReasoningTool use
QW
Qwen3.8 Flash Next GGUF mirror
Qwen · hyukudan
Params177B
Context256K
Smallest2.8 GB
ReasoningTool use
GE
gemma 4 12B it qat
Gemma · TheHunter2623
Params11.9B
Context256K
Smallest0.3 GB
ReasoningTool useVision
DE
DeepSeek-V4.1-Flash-1017
DeepSeek · webmp3
Params748B
Context1024K
Smallest382.4 GB
ReasoningTool use
GE
Gemma-4-E2B-It
Gemma · Charles322
Params4.65B
Context128K
Smallest2.3 GB
ReasoningTool useVision
GE
gemma 3 4b it unslop GSPO
Gemma · electroglyph
Params3.88B
Context128K
Smallest2.5 GB
Vision
QW
Qwen3 Coder Next REAP 48B A3B
Qwen · Ai2-Alliance
Params48.9B
Context256K
Smallest22.9 GB
CodingTool use
HU
Huihui Nex N2 mini abliterated
Huihui · quant-mind
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
MI
Minimax-M2.1
Minimax · moxin-org
Params229B
Context192K
Smallest84.9 GB
ReasoningTool use
QW
kuza qwen 3.5 4b quant study
Qwen · kuzaai
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool use

Other quants

Keep browsing