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
NU
NuminaMath-7B-TIR
Numinamath · legraphista
Params6.91B
Context4K
Smallest1.7 GB
GGUF
GE
Gemma 4 26B A4B It Claude Opus Distill
Gemma · TeichAI
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningVision
QW
Qwen3-Reranker-4B
Qwen · gorse-io
Params4.02B
Context40K
Q4_K_M2.5 GB
EmbeddingReasoningTool use
AU
Austral 24B Winton
Austral · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
RW
rwkv 6 finch 1b6
Rwkv · latestissue
Params1.6B
Context1024K
Smallest0.7 GB
GGUF
OP
Openhands Lm 7b v0.1
Openhands · bartowski
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
GE
Gemma 4 12B It Esper4
Gemma · bartowski
Params11.9B
Context256K
Q4_K_M7.7 GB
CodingReasoningVision
FA
Falcon-H1-3B-Instruct
Falcon · unsloth
Params3.15B
Context128K
Q4_K_M1.9 GB
GGUF
QW
Qwen3 VL 2B Thinking
Qwen · bartowski
Params1.72B
Context256K
Q4_K_M1.1 GB
ReasoningVision
NE
NeoHorse-Jev-4B Q4_K_M unified decision + vision
Neohorse · TokenRhythm
Params4.2B
Context256K
Q4_K_M3.4 GB
Vision
QW
Qwen2.5-Vl-7B-Instruct
Qwen · mnsims1024
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
YO
Youtu-VL-4B-Instruct
Youtu · Mungert
Params4.9B
Context32K
Q4_K_M3.1 GB
Vision
QW
DS R1 Qwen3 8B ArliAI RpR v4 Small
Qwen · Lewdiculous
Params8.19B
Context128K
Q4_K_M5.0 GB
ReasoningRoleplay
QW
Qwen3.5 27B RpRMax v1
Qwen · bartowski
Params27B
Context256K
Q4_K_M17.5 GB
Vision
MI
Mizan v3 3B
Mizan · bartowski
Params2.9B
Context256K
Q4_K_M2.0 GB
Vision
QW
cyberneurova Qwen3.8 Flash Next
Qwen · Merlinoz11
Params177B
Context256K
Q4_K_M119.9 GB
ReasoningTool useVision
BO
NbAiLab/borealis2-26b-a4b-preview
Borealis · NbAiLab
Params25.2B
Context256K
Q4_K_M16.8 GB
Vision
WA
Wan2.1 Fun 14B Control
Wan · city96
Params16.4B
Context—
Q4_K_M10.9 GB
GGUF
OR
Ornith 1.0 35B MTP
Ornith · SC117
Params447M
Context256K
Smallest14.3 GB
ReasoningVision
LF
LFM2.5-350M
Lfm · ensu-app
Params354M
Context125K
Q4_K_M0.2 GB
Tool use
GR
granite 4.2 3b
Granite · NANI-Nithin
Params3.66B
Context128K
Q4_K_M2.2 GB
ReasoningTool use
QW
Qwen2.5 0.5B
Qwen · mradermacher
Params494M
Context32K
Q4_K_M0.4 GB
Tool use
MI
Mistral-7B-v0.3
Mistral · legraphista
Params7.25B
Context32K
Smallest1.6 GB
GGUF
TR
Trinity Mini
Trinity · bartowski
Params26B
Context128K
Q4_K_M15.9 GB
GGUF
AL
AliceAI Foundation 80B A3B Base
Aliceai · robolamp
Params79.6B
Context256K
Q4_K_M49.5 GB
GGUF
GE
Gemma 2 2b
Gemma · legraphista
Params2.61B
Context8K
Smallest0.8 GB
GGUF
MI
Magistral Small 2507
Mistral · bartowski
Params23.6B
Context40K
Q4_K_M14.3 GB
Reasoning
QW
jinaai/test-qwen25-coder-jina-code-embeddings-1.5b
Qwen · jinaai
Params1.54B
Context32K
Smallest0.4 GB
CodingEmbedding
QW
Qwen3.5 9B Star Trek TNG DS9 Heretic Uncensored Thinking MAX NEOCODE
Qwen · DavidAU
Params8.95B
Context256K
Q4_K_M6.8 GB
ReasoningRoleplayVision
GE
Amoral Gemma3 12B
Gemma · bartowski
Params11.8B
Context128K
Q4_K_M7.3 GB
Roleplay

Other quants

Keep browsing