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
QW
Negentropy claude opus 4.7 9B
Qwen · Jackrong
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningVision
SK
Skywork OR1 32B Preview
Skywork · bartowski
Params32.8B
Context128K
Q4_K_M19.9 GB
GGUF
NE
NeoHorse 1 4B Max Heretic Uncensored TURBO
Neohorse · prithivMLmods
Params4.21B
Context256K
Q4_K_M2.7 GB
Tool use
MI
MiniCPM V 4.6 Thinking Heretic MTP
MiniCPM · MuXodious
Params773M
Context256K
Smallest0.6 GB
ReasoningVision
QW
Qwen3 VisionCaption 2B
Qwen · prithivMLmods
Params1.72B
Context256K
Smallest1.8 GB
Vision
GL
cerebras/GLM-4.7-REAP-218B-A32B
GLM · unsloth
Params218B
Context198K
Q4_K_M132.0 GB
GGUF
GR
granite-4.0-micro-base
Granite · Mungert
Params3.4B
Context128K
Q4_K_M2.1 GB
GGUF
NE
Nemotron 3 Nano 4B
Nemotron · bartowski
Params3.97B
Context1024K
Q4_K_M3.0 GB
Tool use
LF
Lfm2.5-Vl-1.6B
Lfm · unsloth
Params1.17B
Context125K
Q4_K_M0.7 GB
Vision
OS
Osmosis Mcp 4b
Osmosis · osmosis-ai
Params4.41B
Context40K
Q4_K_M2.7 GB
GGUF
GE
Gemma 4 31B It Claude Opus Distill v2
Gemma · TeichAI
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningVision
SN
Snowflake Arctic Embed L v2.0
Snowflake · Casual-Autopsy
Params567M
Context8K
Q4_K_M0.4 GB
Embedding
QW
Qwen Image Edit 2511
Qwen · w3ss
Params20.4B
Context—
Q4_K_M13.2 GB
GGUF
QW
trashpanda org QwQ 32B Snowdrop v0
Qwen · bartowski
Params32.8B
Context128K
Q4_K_M19.8 GB
Reasoning
LL
Llama-3_3-Nemotron-Super-49B-V1
Llama · unsloth
Params49.9B
Context128K
Q4_K_M30.2 GB
Coding
FA
Fara 7B
Fara · bartowski
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
NE
OpenMath Nemotron 14B Kaggle
Nemotron · bartowski
Params14.8B
Context128K
Q4_K_M9.0 GB
Reasoning
GE
Huihui Gemma 4 26B A4B It Abliterated
Gemma · bullerwins
Params25.2B
Context256K
Q4_K_M16.8 GB
GGUF
RU
RusMind 4.5.4 Momentum
Rusmind · DICPlay
Params4.65B
Context128K
Q4_K_M3.4 GB
ReasoningTool use
DO
Dots.Mocr
Dots · prithivMLmods
Params1.78B
Context128K
Q4_K_M1.1 GB
CodingVision
LI
Ling-3.0-tiny-base-30T
Ling · FriskyFennec
Params8.2B
Context8K
Q4_K_M5.0 GB
GGUF
QW
Qwen2.5 0.5B Instruct
Qwen · legraphista
Params494M
Context32K
Smallest0.3 GB
GGUF
JE
Jebadiah 9b v2 1
Jebadiah · bartowski
Params9.2B
Context256K
Q4_K_M6.0 GB
Vision
GE
Gemma 4 26B A4B It Qat
Gemma · prithivMLmods
Params25.2B
Context256K
Q4_K_M16.8 GB
Vision
GE
Gemma-4-E4B-It
Gemma · Hlebek
Params7.52B
Context128K
Q4_K_M5.0 GB
ReasoningTool useVision
CO
ContextPilot 14B
Contextpilot · bartowski
Params14.8B
Context40K
Q4_K_M9.3 GB
Tool use
CY
Cydonia 24B v3
Cydonia · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
SM
SmolLM2-135M
SmolLM · ggml-org
Params135M
Context8K
Q4_K_M0.1 GB
GGUF
AT
Athene 70B
Athene · legraphista
Params70.6B
Context8K
Smallest15.3 GB
GGUF
QW
Qwen2.5 Gutenberg Doppel 32B
Qwen · bartowski
Params32.8B
Context32K
Q4_K_M19.9 GB
GGUF

Other quants

Keep browsing