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.
GE
Gemma 4 26B A4B It Abliterated
Gemma · SevenOfNine
Params25.2B
Context256K
Smallest19.1 GB
LF
LFM2.5-24B-A2B
Lfm · ggml-org
Params24B
Context128K
Q4_K_M14.5 GB
CA
Carnice V3
Carnice · bartowski
Params27.3B
Context256K
Q4_K_M17.8 GB
QW
Qwen3.8-Flash-Next-DFlash2
Qwen · incoai
Params603M
Context256K
Q4_K_M0.4 GB
CL
clef flash
Clef · NANI-Nithin
Params8.95B
Context256K
Q4_K_M5.6 GB
QW
Qwen3.6 27B Abliterated Heretic Uncensored BF16 v4
Qwen · Youssofal
Params27B
Context256K
Q4_K_M16.5 GB
LO
LongCat Flash Lite
Longcat · InquiringMinds-AI
Params68.6B
Context320K
Q4_K_M40.2 GB
GR
Grug 27b
Grug · bartowski
Params27B
Context256K
Q4_K_M17.5 GB
HU
HunyuanVideo I2V
Hunyuanvideo · city96
Params12.8B
Context—
Q4_K_M7.9 GB
NE
Nemotron Cascade 8B Thinking
Nemotron · bartowski
Params8.19B
Context32K
Q4_K_M5.0 GB
QW
Qwen2-1.5B
Qwen · legraphista
Params1.54B
Context128K
Smallest0.4 GB
BO
prism ml Bonsai 8B unpacked
Bonsai · bartowski
Params8.19B
Context64K
Q4_K_M5.2 GB
OR
Ornith 1.5 35B A3B Abliterated
Ornith · PocketAiHub
Params34.7B
Context256K
Q4_K_M21.2 GB
MI
Mimo-V2.5
Mimo · unsloth
Params310B
Context1024K
Q4_K_M190.9 GB
DE
DeepSeek V4 Flash 0731
DeepSeek · ggml-org
Params284B
Context—
Smallest10.8 GB
LL
Llama Guard 3 8B
Llama · legraphista
Params8B
Context128K
Smallest2.0 GB
QW
Qwen3.8 27B Uncensored JoyFox Aggressive
Qwen · joyfox
Params27.3B
Context256K
Q4_K_M16.5 GB
IM
Z Image Turbo
Image · vantagewithai
Params6.15B
Context—
Q4_K_M5.0 GB
CO
C4Ai Command R7B 12 2024
Command R · bartowski
Params8B
Context8K
Q4_K_M5.1 GB
GR
Granite 4.0 H Tiny
Granite · bartowski
Params6.94B
Context1024K
Q4_K_M4.3 GB
GP
kldzj gpt oss 120b heretic v2
gpt-oss · bartowski
Params117B
Context—
Smallest0.2 GB
GE
Gemma-4-E4B-It
Gemma · ente-ai
Params7.5B
Context128K
Q4_K_M5.0 GB
MI
Voxtral Small 24B 2507
Mistral · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB
DE
Qwen2.5 32B
DeepSeek · bartowski
Params32.8B
Context128K
Q4_K_M19.9 GB
QW
Qwen2-1.5B-Instruct
Qwen · legraphista
Params1.54B
Context32K
Smallest0.4 GB
HU
Hunyuan 1.8B Instruct
Hunyuan · bartowski
Params1.79B
Context256K
Q4_K_M1.1 GB
QW
Qwen3.8 27B Humanlike Chat
Qwen · Guile
Params27B
Context256K
Q4_K_M16.6 GB
GE
Gemma 4 Gembrain 31B It Uncensored Heretic
Gemma · llmfan46
Params30.7B
Context256K
Q4_K_M18.7 GB
GR
Granite 4.0 350m
Granite · ibm-granite
Params352M
Context32K
Q4_K_M0.2 GB
CY
Cydonia 24B v4.1
Cydonia · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB