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
YU
YuE2 audio tokenizer, the v9 head of Mothersuperior, on MERT-v2-FullSong
Yue · Serveurperso
Params632M
Context—
Smallest0.0 GB
GGUF
QW
Qwen3.8-27B
Qwen · unsloth
Params27.3B
Context256K
Q4_K_M16.5 GB
Vision
OR
Ornith-1.5-9B
Ornith · ornith-ai
Params9.2B
Context256K
Q4_K_M5.8 GB
Vision
OR
Ornith-1.5-35B
Ornith · ornith-ai
Params35.5B
Context256K
Q4_K_M21.7 GB
Vision
QW
Qwen3.8-27B
Qwen · huihui-ai
Params27.3B
Context256K
Q4_K_M16.6 GB
Vision
OR
Ornith 1.0 9B
Ornith · ornith-ai
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
QW
Qwen3.8-27B
Qwen · ggml-org
Params3B
Context256K
Q4_K_M19.0 GB
Vision
QW
Qwen Image 2.1 Uncensored Quantized
Qwen · abenzerps
Params7.12B
Context—
Q4_K_M4.6 GB
GGUF
QW
Qwen3.5 9B The Defiant Fable Uncensored Heretic NEO IMATRIX MAX MTP
Qwen · DavidAU
Params8.95B
Context256K
Q4_K_M6.8 GB
CodingReasoningRoleplay
GE
Gemma-4-12B-It
Gemma · unsloth
Params11.9B
Context256K
Q4_K_M7.1 GB
Vision
VI
VieNeu-TTS-v3-Turbo-staging
Vieneu · pnnbao-ump
Params146M
Context—
Smallest0.2 GB
GGUF
OR
Ornith 1.0 35B
Ornith · ornith-ai
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
QW
Qwen3.5-9B
Qwen · unsloth
Params8.95B
Context256K
Q4_K_M5.7 GB
Vision
QW
Qwen3.6-35B-A3B
Qwen · unsloth
Params34.7B
Context256K
Q4_K_M22.1 GB
Vision
QW
Qwen3.6-35B-A3B
Qwen · unsloth
Params35.5B
Context256K
Q4_K_M22.7 GB
Vision
QW
Qwen3.5-4B
Qwen · unsloth
Params4.21B
Context256K
Q4_K_M2.7 GB
Vision
CO
Cohere Transcribe
Cohere · handy-computer
Params2.05B
Context—
Q4_K_M1.6 GB
GGUF
QW
Qwen3.8 35B A3B Distill
Qwen · empero-ai
Params35.5B
Context256K
Q4_K_M21.7 GB
ReasoningVision
GE
Gemma-4-26B-A4B-It
Gemma · unsloth
Params25.2B
Context256K
Q4_K_M16.9 GB
Vision
QW
Qwen3.8 Flash Next
Qwen · unsloth
Params177B
Context256K
Q4_K_M1.9 GB
Vision
IM
Z Image Turbo
Image · unsloth
Params6.15B
Context—
Q4_K_M3.9 GB
GGUF
QW
Qwen3.5-35B-A3B
Qwen · unsloth
Params34.7B
Context256K
Q4_K_M22.0 GB
Vision
QW
MiMo V2.6 Distill Qwen 9B
Qwen · bartowski
Params8.95B
Context256K
Q4_K_M5.8 GB
CodingTool useVision
QW
Qwopus3.8 27B Flash V2
Qwopus · Jackrong
Params28B
Context256K
Q4_K_M16.8 GB
CodingReasoningTool use
GL
GLM 5.3 Flash
GLM · unsloth
Params320B
Context1024K
Smallest93.1 GB
Vision
MI
MiniMax-Music3 flow matching DiT
Minimax · Serveurperso
Params2.4B
Context—
Q4_K_M1.4 GB
GGUF
MU
Muse Glimmer 30B
Muse · unsloth
Params27.9B
Context128K
Smallest1.6 GB
Vision
HI
Higgs Audio v3 Studio
Higgs · drbaph
Params4.65B
Context—
Q4_K_M4.1 GB
GGUF
QW
Qwen Image Edit 2511
Qwen · unsloth
Params20.4B
Context—
Q4_K_M12.8 GB
GGUF
QW
Qwen3-TTS-Tokenizer-12Hz
Qwen · Serveurperso
Params1.9B
Context—
Q4_K_M0.3 GB
GGUF

What is BF16?

Unquantized bfloat16. Original quality and the largest size. On average it stores about 16 bits per weight, so a BF16 file is roughly 100% of the size of the same model in 16-bit. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

9,004 models have a BF16 file on ggufmodels.com, and those files range from 0.0 to 4893.2 GB. The most downloaded are YuE2 audio tokenizer, the v9 head of Mothersuperior, on MERT-v2-FullSong, Qwen3.8-27B and Ornith-1.5-9B. For a longer explanation of every quant type, read GGUF quantization explained.

Frequently asked questions

What is BF16 in GGUF?

Unquantized bfloat16. Original quality and the largest size. It averages about 16 bits per weight.

Should I use BF16?

The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

How big is a BF16 file?

BF16 files on this site range from 0.0 to 4893.2 GB, depending on the model. As a rule of thumb it is about 100% of the 16-bit size.

Other quants

Keep browsing