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
GE
Huihui gemma 4 12B it qat q4 0 unquantized abliterated
Gemma · huihui-ai
Params11.9B
Context256K
Smallest0.9 GB
Vision
CH
Chroma1 HD
Chroma · silveroxides
Params8.9B
Context—
Q4_K_M5.6 GB
GGUF
FR
FrogNano 4B 2609
Frognano · bartowski
Params4.33B
Context256K
Q4_K_M2.8 GB
Vision
QW
Qwen Image
Qwen · city96
Params20.4B
Context—
Q4_K_M13.1 GB
GGUF
QW
Qwen Image 2.1 Turbo Uncensored
Qwen · TechnoBaptist
Params8.2B
Context256K
Smallest3.3 GB
CodingVision
LI
H2O Lightning 4B
Lightning · h2oai
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
OM
OmniVoice-tokenizer
Omnivoice · Serveurperso
Params613M
Context—
Q4_K_M0.3 GB
GGUF
NE
Nvidia-Nemotron-3.5-Lightning-30B-A3B
Nemotron · unsloth
Params32.9B
Context1024K
Q4_K_M25.3 GB
GGUF
GE
Winnow E4B
Gemma · EldanRing
Params78M
Context128K
Smallest0.2 GB
Vision
QW
Qwen3-30B-A3B
Qwen · unsloth
Params30.5B
Context40K
Q4_K_M18.6 GB
GGUF
GR
Granite Speech 4.1 2B NAR
Granite · handy-computer
Params2.25B
Context—
Q4_K_M1.6 GB
GGUF
LL
Llama-3.2-1B-Instruct
Llama · unsloth
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
GL
Glm-4.5-Air
GLM · unsloth
Params110B
Context128K
Q4_K_M73.0 GB
GGUF
DE
Deepseek-R1-Distill-Llama-8B
DeepSeek · unsloth
Params8B
Context128K
Q4_K_M4.9 GB
Reasoning
D1
d1 3B
LiquidAI
Params2.7B
Context32K
Q4_K_M1.7 GB
Vision
OR
Ornith 1.5 35B A3B
Ornith · bartowski
Params35.5B
Context256K
Q4_K_M21.9 GB
Vision
FL
FLUX.1 dev
Flux · unsloth
Params11.9B
Context—
Q4_K_M6.9 GB
GGUF
CL
Clef Flash
Clef · bartowski
Params9.1B
Context256K
Q4_K_M6.0 GB
CodingVision
CL
Cloudflare clef
Clef · bartowski
Params27B
Context256K
Q4_K_M17.7 GB
CodingVision
GR
Granite Speech 4.1 2B
Granite · handy-computer
Params2.31B
Context—
Q4_K_M1.6 GB
GGUF
FU
Fun ASR MLT Nano 2512
Fun · handy-computer
Params830M
Context—
Q4_K_M0.6 GB
GGUF
QW
Qwen3 TTS 12Hz 1.7B Base
Qwen · ggml-org
Params1.73B
Context32K
Q4_K_M1.0 GB
Vision
LT
LTX 2
Ltx · unsloth
Params18.9B
Context—
Q4_K_M12.8 GB
GGUF
MI
Mistral-7B-Instruct-v0.3
Mistral · thesven
Params7B
Context32K
Q4_K_M4.4 GB
GGUF
LL
Llama-4-Scout-17B-16E-Instruct
Llama · unsloth
Params108B
Context10240K
Q4_K_M65.4 GB
Vision
QW
Qwen3.5 35B A3B
Qwen · bartowski
Params35.5B
Context256K
Q4_K_M22.3 GB
Vision
OR
Ornith 1.5 9B
Ornith · AtomicChat
Params8.95B
Context256K
Smallest2.8 GB
ReasoningTool useVision
GL
Glm-4.6V-Flash
GLM · unsloth
Params9.4B
Context128K
Q4_K_M6.2 GB
Vision
OR
Orion 26B A4B v1.1
Orion · bartowski
Params25.2B
Context256K
Q4_K_M18.0 GB
Vision
QW
Qwen3 ASR 1.7B
Qwen · ggml-org
Params2.03B
Context64K
Smallest2.2 GB
Vision

Other quants

Keep browsing