BF16 GGUF models

Unquantized bfloat16. Original quality and the largest size. 9004 models have a BF16 file. Sizes run from 1M to 2780B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
GR
Granite 4.0 3B Vision BE
Granite · taronaeo
Params3.66B
Context128K
Q4_K_M2.2 GB
GGUF
LA
amazon LAR 9B
Lar · prithivMLmods
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
FA
FaithEyes 8B RL
Faitheyes · prithivMLmods
Params8.19B
Context256K
Q4_K_M5.0 GB
CodingTool useVision
QW
Huihui ai Qwen3.5 2B Abliterated
Qwen · Spellman66
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool useVision
QW
MTP Qwen3.5 122B A10B
Qwen · tomngdev
Params4.05B
Context256K
Q4_K_M3.2 GB
ReasoningTool use
NE
Nex N2 Mini
Nex · adamm-hf
Params34.7B
Context256K
Q4_K_M21.4 GB
ReasoningTool useVision
QW
Qwen3-16B-A3B
Qwen · Mungert
Params16B
Context40K
Q4_K_M10.0 GB
GGUF
TA
talkie 1930 13b it
Talkie · thomasgauthier
Params13.3B
Context2K
Q4_K_M8.6 GB
GGUF
SU
Supertron3 0.8B
Supertron · prithivMLmods
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
ZW
ZwZ2 9B
Zwz · prithivMLmods
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
OS
Osmosis Structure 0.6B
Osmosis · osmosis-ai
Params596M
Context40K
Q4_K_M0.4 GB
GGUF
LT
LTX 2.3 DISTILLED
Ltx · FenomAI
Params21B
Context—
Q4_K_M14.2 GB
GGUF
QW
Qwen3.8-27B
Qwen · Aydge
Params27.3B
Context256K
Q4_K_M16.6 GB
Vision
LL
Llama 3.1 8B UltraLong 1M Instruct
Llama · bartowski
Params8B
Context1048K
Q4_K_M4.9 GB
GGUF
QW
qwenimage21
Qwen · wwdsada
Params7.12B
Context—
Q4_K_M4.2 GB
GGUF
IN
Internvl3-38B-Instruct
Internvl · unsloth
Params32.8B
Context32K
Q4_K_M19.8 GB
CodingTool useVision
GE
humanizer-12b
Gemma · suryatmodulus
Params11.9B
Context256K
Q4_K_M7.6 GB
Vision
RE
Reka Flash 3.1
Reka · bartowski
Params20.9B
Context96K
Q4_K_M13.6 GB
GGUF
NE
Nemotron 3.5 Embed 1B
Nemotron · maternion
Params1.14B
Context256K
Smallest0.9 GB
EmbeddingVision
QW
Qwen3.8-27B
Qwen · Didkk
Params27.3B
Context256K
Q4_K_M16.6 GB
Vision
GE
Gemma 4 E4B It Qat
Gemma · prithivMLmods
Params7.46B
Context128K
Q4_K_M5.3 GB
ReasoningTool useVision
QW
uml to plantuml qwen3.5 4b
Qwen · Seym0n
Params4.21B
Context256K
Q4_K_M2.7 GB
CodingReasoningTool use
NU
NuExtract 2.0 8B
Nuextract · numind
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
AQ
Aquif 3.5 8B Think
Aquif · bartowski
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
QW
qwen image edit
Qwen · badgame
Params20.4B
Context—
Smallest11.5 GB
GGUF
QW
Qwen3 Coder Next REAP 40B A3B
Qwen · lovedheart
Params41B
Context256K
Smallest20.0 GB
CodingTool use
QW
Qwen3.5 9B Fable 5 v1
Qwen · TeichAI
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
NE
Nemotron-3.5-Embed-8B
Nemotron · maternion
Params7.95B
Context256K
Q4_K_M4.9 GB
EmbeddingVision
QW
Qwen Image 2.1 Uncensored
Qwen · kacakto
Params7.12B
Context—
Q4_K_M4.6 GB
GGUF
OP
OpenThinker3 7B
Openthinker · bartowski
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use

Other quants

Keep browsing