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
GA
gaggle-nanochat-pretrained-climbmix-20260924
Gaggle · castorini
Params3.3B
Context2K
Q4_K_M2.6 GB
Coding
QW
QwenDGAF Coder 0.5B
Qwen · hecan3d
Params494M
Context32K
Q4_K_M0.4 GB
CodingRoleplayTool use
HE
Heimdallr 27B v0.35
Heimdallr · ReadyArt
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayTool use
GR
Granite-3.3-2B-Instruct
Granite · unsloth
Params2.53B
Context128K
Q4_K_M1.5 GB
GGUF
MA
Trappu Magnum Picaro 0.7 v2 12b
Magnum · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
GE
Gemma-3-4B-It-Qat-Int4
Gemma · unsloth
Params3.88B
Context128K
Q4_K_M2.3 GB
Vision
EX
EXAONE 4.0.1 32B
Exaone · bartowski
Params32B
Context128K
Q4_K_M19.3 GB
GGUF
DE
Huihui DeepSeek V4 Flash 0731 abliterated
DeepSeek · Justbackup
Params284B
Context—
Smallest10.9 GB
GGUF
DE
DeepSeek R1 Zero BF16
DeepSeek · unsloth
Params671B
Context160K
Q4_K_M404.4 GB
Reasoning
AB
Absolute_Zero_Reasoner Coder 7b
Absolute · bartowski
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
GE
Bella Bartender Gemma E4B Src
Gemma · juiceb0xc0de
Params7.46B
Context128K
Q4_K_M5.3 GB
GGUF
LL
Meta Llama 3.1 8B Instruct
Llama · legraphista
Params8B
Context128K
Smallest2.0 GB
GGUF
TE
Tessa T1 14B
Tessa · bartowski
Params14.8B
Context117K
Q4_K_M9.0 GB
GGUF
MI
ministral 3 8b reasoning 2512
Mistral · nile-academy
Params8.49B
Context256K
Q4_K_M5.2 GB
ReasoningTool useVision
QW
Qwen2.5 Math 1.5B Instruct
Qwen · legraphista
Params1.54B
Context4K
Smallest0.4 GB
Tool use
QW
Qwen3.8 27B Abliterated SFT
Qwen · jenerallee78
Params27.3B
Context256K
Q4_K_M16.8 GB
Vision
JA
Jan Nano
Jan · bartowski
Params4B
Context40K
Q4_K_M2.5 GB
GGUF
QW
Qwythos 9B Claude Mythos 5 1M
Qwythos · N8STORM
Params8.95B
Context1024K
Q4_K_M5.6 GB
ReasoningTool useVision
GE
gemma-4-E4B-it
Gemma · Mungert
Params7.52B
Context128K
Q4_K_M6.2 GB
ReasoningTool use
D1
d1 3B
prithivMLmods
Params2.7B
Context32K
Q4_K_M1.7 GB
ReasoningTool useVision
NA
Nanbeige4.3 33B
Nanbeige · csdhall
Params33.1B
Context512K
Q4_K_M20.1 GB
ReasoningTool use
QW
Qwen3.5 27B Claude Opus 4.6 Distill
Qwen · TeichAI
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
GL
cerebras/GLM-4.6-REAP-268B-A32B
GLM · unsloth
Params269B
Context198K
Q4_K_M162.5 GB
ReasoningTool use
QW
Qwen Image 2.1 Uncensored
Qwen · wazimondo
Params7.12B
Context—
Q4_K_M4.6 GB
GGUF
GL
GLM 4.5 Air REAP 82B A12B heretic
GLM · jtl11
Params82B
Context128K
Q4_K_M53.9 GB
GGUF
FU
Functiongemma 270m It
Functiongemma · ggml-org
Params268M
Context32K
Smallest0.3 GB
Tool use
OC
occamy 1.0 mtp
Occamy · moontato
Params1.86B
Context256K
Q4_K_M1.3 GB
GGUF
LI
A.X-4.0-Light
Light · Mungert
Params7.26B
Context16K
Q4_K_M4.5 GB
GGUF
ME
Mellum2.1 12B A2.5B Thinking
Mellum · prithivMLmods
Params12.1B
Context128K
Q4_K_M8.1 GB
ReasoningTool use
CO
VL 1 Coder Heretic
Coder · haffner
Params7.62B
Context32K
Smallest1.4 GB
CodingReasoningTool use

Other quants

Keep browsing