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
CL
Clef Flash
Clef · prithivMLmods
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingVision
GI
GigaChat 20B A3B instruct v1.5
Gigachat · ai-sage
Params20.6B
Context128K
Q4_K_M12.5 GB
GGUF
NE
NeuTTS Air
Neutts · BricksDisplay
Params262M
Context—
Q4_K_M0.3 GB
GGUF
EM
xVITA Embed2 zhTW
Embeddinggemma · xCloudinfo
Params271M
Context256K
Q4_K_M0.2 GB
EmbeddingVision
VI
VibeThinker 3B
Vibethinker · prithivMLmods
Params3.09B
Context128K
Q4_K_M1.9 GB
CodingReasoning
QW
VulnLLM-R-7B
Qwen · Mungert
Params7.6B
Context32K
Q4_K_M4.9 GB
CodingReasoning
GE
Gemma-4-26B-A4B-It-Ultra-Uncensored-Heretic
Gemma · JMingo
Params25.2B
Context256K
Q4_K_M16.9 GB
GGUF
IN
InternVL3_5 1B
Internvl · bartowski
Params752M
Context40K
Q4_K_M0.5 GB
Vision
CY
Cydonia R1 24B v4.1
Cydonia · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB
Reasoning
QW
Qwen3.5 27B Instruct Uncensored
Qwen · backpropSukuna
Params27B
Context256K
Q4_K_M16.5 GB
Vision
LF
LFM2 8B A1B
Lfm · bartowski
Params8.34B
Context125K
Q4_K_M5.1 GB
GGUF
AP
Apriel 1.5 15b Thinker
Apriel · bartowski
Params14.4B
Context256K
Q4_K_M8.8 GB
ReasoningVision
QW
UD 2.0 Qwen3.6 35B A3B Claude 4.6 Opus Reasoning Distilled
Qwen · mfielding92
Params34.7B
Context256K
Q4_K_M22.1 GB
ReasoningVision
AF
AFM 4.5B
Afm · bartowski
Params4.62B
Context64K
Q4_K_M2.9 GB
GGUF
LI
Ling Mini 2.0
Ling · bartowski
Params16.3B
Context32K
Q4_K_M9.9 GB
GGUF
NE
Nemotron Cascade 8B
Nemotron · bartowski
Params8.19B
Context32K
Q4_K_M5.0 GB
Reasoning
TH
thinksound
Thinksound · ilintar
Params—
Context—
Smallest0.0 GB
GGUF
RA
X Ray_Alpha
Ray · bartowski
Params3.88B
Context128K
Q4_K_M2.5 GB
Vision
QW
Qwen Image 2.1 Turbo Uncensored
Qwen · li1272
Params8.2B
Context256K
Smallest3.3 GB
CodingVision
MO
Motif Video 2B
Motif · Motif-Technologies
Params2.04B
Context—
Q4_K_M1.2 GB
GGUF
GR
Granite Guardian 4.1 8b
Granite · mrutkows
Params8.38B
Context128K
Q4_K_M5.1 GB
Tool use
YA
YanoljaNEXT Rosetta 12B 2510
Yanoljanext · bartowski
Params12.8B
Context128K
Q4_K_M7.9 GB
GGUF
GE
gemma-4-31B-it-uncensored-heretic
Gemma · JMingo
Params30.7B
Context256K
Q4_K_M18.3 GB
GGUF
NE
nvidia OpenCodeReasoning Nemotron 14B
Nemotron · bartowski
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingReasoning
QW
Qwen Image 2.1 Uncensored HF
Qwen · NeverWantedJr
Params7.12B
Context—
Q4_K_M4.6 GB
GGUF
LL
Llama 3.1 8B UltraLong 4M Instruct
Llama · bartowski
Params8B
Context4192K
Q4_K_M4.9 GB
GGUF
GE
gemma-4-12B
Gemma · ggml-org
Params11.9B
Context256K
Smallest12.7 GB
GGUF
GL
Glm-4.7-Flash
GLM · bloopez
Params30B
Context198K
Smallest59.9 GB
GGUF
GE
GemmaDGAF 2B
Gemma · hecan3d
Params2.6B
Context8K
Q4_K_M1.7 GB
Roleplay
FO
FoodGuard 4B
Foodguard · bartowski
Params4.41B
Context32K
Q4_K_M2.8 GB
GGUF

Other quants

Keep browsing