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.
QW
Qwen3.5 27B Writer
Qwen · bartowski
Params26.9B
Context256K
Q4_K_M17.5 GB
QW
Qwen3.6 27B MTP pi reasoning
Qwen · bytkim
Params27.3B
Context256K
Q4_K_M16.8 GB
BR
Breeze TTS 2
Breeze · agentory
Params—
Context—
Smallest4.3 GB
VE
UI Venus 2 9B
Venus · prithivMLmods
Params8.95B
Context256K
Q4_K_M5.6 GB
QW
Qwen3-14B
Qwen · cmp-nct
Params14.8B
Context40K
Q4_K_M9.0 GB
MI
Midm-2.0-Base-Instruct
Midm · Mungert
Params11.5B
Context32K
Q4_K_M7.1 GB
SU
Supra 1.5 50M Instruct Exp Gguf Src
Supra · SupraLabs
Params52M
Context5K
Q4_K_M0.0 GB
NE
NVIDIA Nemotron Nano 12B v2 VL BF16
Nemotron · Vastined
Params12.3B
Context1024K
Q4_K_M7.5 GB
GE
Gemma 3n E4B It Absolute Heresy MPOA
Gemma · MuXodious
Params6.87B
Context32K
Q4_K_M4.2 GB
QW
Qwen3.8 0.6B
Qwen · piskle
Params596M
Context40K
Q4_K_M0.4 GB
ST
Cerebras Step 3.5 Flash REAP 149B A11B
Step · wimmmm
Params149B
Context256K
Smallest0.4 GB
GE
Gemma 3 Starshine 12B
Gemma · bartowski
Params11.8B
Context128K
Q4_K_M7.3 GB
LL
OpenMath-CodeLlama-7b-Python-hf
Llama · Mungert
Params6.74B
Context16K
Q4_K_M4.1 GB
LF
LFM3 Audio 2B
Lfm · prithivMLmods
Params1.73B
Context125K
Q4_K_M1.1 GB
QW
Qwen3.5-9B
Qwen · cmp-nct
Params8.95B
Context256K
Q4_K_M5.7 GB
LL
Schematron-3B
Llama · Mungert
Params3.21B
Context128K
Q4_K_M2.0 GB
IM
ImageShield MMCF 2B Vl
Imageshield · prithivMLmods
Params1.72B
Context256K
Q4_K_M1.1 GB
OV
OvisOCR2
Ovisocr · prithivMLmods
Params752M
Context256K
Q4_K_M0.5 GB
QW
Negentropy claude opus 4.7 4B
Qwen · Jackrong
Params4.2B
Context256K
Q4_K_M2.7 GB
QW
Gliese Qwen3.5 4B Abliterated Caption
Qwen · prithivMLmods
Params4.21B
Context256K
Smallest4.5 GB
PH
Phi 3 mini 128k instruct iMat
Phi · qwp4w3hyb
Params3.82B
Context128K
Q4_K_M2.4 GB
LF
lfm3 1.7B abliter8
Lfm · abliter8-ai
Params1.73B
Context256K
Q4_K_M1.1 GB
QW
nla qwen2.5 7b L20 ar
Qwen · thomasgauthier
Params5.45B
Context32K
Q4_K_M3.4 GB
LF
LFM2.5-24B-A2B-Preview
Lfm · TechnoBaptist
Params24B
Context128K
Smallest7.5 GB
QW
qwen3.5 0.8b
Qwen · nile-academy
Params773M
Context256K
Q4_K_M0.5 GB
TH
P110-ThaiOCR-4B
Thaiocr · PorsukR
Params4.33B
Context256K
Q4_K_M2.8 GB
EM
emma 6
Emma · MrMeOrYou
Params1.55B
Context4K
Q4_K_M1.0 GB
LL
Llama-3.3-70B-Instruct
Llama · axana-labs
Params70.6B
Context128K
Q4_K_M42.5 GB
QW
Qwen3.5 35B A3B Uncensored Heretic v2 Native MTP Preserved NVFP4 Experts Only
Qwen · llmfan46
Params35.5B
Context256K
Smallest21.7 GB
QW
Qwen3.8-27B
Qwen · a4lg
Params2.97B
Context256K
Q4_K_M2.1 GB