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
SW
Swift-1.5-Ornith-9B
Swift · ukisai
Params9.2B
Context256K
Q4_K_M5.8 GB
ReasoningTool useVision
HO
Homunculus
Homunculus · bartowski
Params12.5B
Context128K
Q4_K_M7.6 GB
GGUF
GE
C2S-Scale-Gemma-2-27B
Gemma · Mungert
Params27.2B
Context8K
Q4_K_M16.7 GB
GGUF
PR
Precog 24B v1
Precog · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
QW
Qwen3.8 Flash Next
Qwen · python-jo
Params177B
Context256K
Q4_K_M1.9 GB
ReasoningTool useVision
QW
Qwen3 4B Kimi2.5 Reasoning Distilled
Qwen · khazarai
Params4B
Context256K
Q4_K_M2.5 GB
Reasoning
KR
krea2_raw
Krea · ChrisColeTech
Params12.8B
Context—
Q4_K_M7.2 GB
GGUF
GE
UNSEEN Gemma 4 26B NSFW
Gemma · 0xSojalSec
Params25.2B
Context256K
Q4_K_M16.8 GB
Vision
GL
GLM 4.7 Flash Heretic
GLM · bartowski
Params29.9B
Context198K
Q4_K_M18.5 GB
GGUF
JA
ja ko vn 12b v2
hell0ks
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
NE
OpenReasoning Nemotron 7B
Nemotron · bartowski
Params7.62B
Context128K
Q4_K_M4.7 GB
Reasoning
GE
Gemma 3 R1 12B v1
Gemma · bartowski
Params11.8B
Context128K
Q4_K_M7.3 GB
Reasoning
FI
FireRed Image Edit 1.0 ComfyUI
Firered · FireRedTeam
Params20.4B
Context—
Q4_K_M13.1 GB
GGUF
QW
Qwen3.5-9B
Qwen · Fix-AI
Params8.95B
Context256K
Q4_K_M5.7 GB
ReasoningTool useVision
QW
QwQ 32B ArliAI RpR v4
Qwen · bartowski
Params32.8B
Context40K
Q4_K_M19.9 GB
Reasoning
MU
Muse-Glimmer-30B-DFlash2
Muse · incoai
Params2.77B
Context128K
Q4_K_M1.6 GB
GGUF
QW
Qwen2.5 7B Instruct
Qwen · legraphista
Params7.62B
Context32K
Smallest1.9 GB
Tool use
GE
Gemma 4 31B It Uncensored Heretic NVFP4
Gemma · llmfan46
Params30.7B
Context256K
Smallest18.0 GB
Vision
TX
Txgemma 9b Chat
Txgemma · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
DE
FuseO1 DeepSeekR1 Qwen2.5 Instruct 32B Preview
DeepSeek · bartowski
Params32.8B
Context128K
Q4_K_M19.9 GB
GGUF
NE
Nemotron 3 Super 120B A12B Uncensored
Nemotron · timteh673
Params121B
Context1024K
Q4_K_M86.1 GB
GGUF
ML
MLExpert
Mlexpert · bartowski
Params34.7B
Context256K
Q4_K_M22.3 GB
CodingReasoningTool use
MI
MiniCPM V 4.7 35B A3B DSpark
MiniCPM · UserSuxx
Params389M
Context256K
Q4_K_M0.2 GB
Vision
CA
Captain Eris Violet GRPO v0.420 GGUF IQ Imatrix
Captain · Lewdiculous
Params12.2B
Context1000K
Q4_K_M7.5 GB
Roleplay
GE
Gemma 3 R1 27B v1
Gemma · bartowski
Params27B
Context128K
Q4_K_M16.5 GB
Reasoning
XL
xLAM 7b R
Xlam · legraphista
Params7.24B
Context32K
Smallest1.6 GB
Tool use
JP
jpt 4b
Jpt · prithivMLmods
Params4.21B
Context256K
Q4_K_M2.7 GB
Vision
QW
Qwen2.5 Coder 1.5B Instruct
Qwen · legraphista
Params1.54B
Context32K
Smallest0.4 GB
CodingTool use
QW
Qwen2.5 72B Instruct
Qwen · legraphista
Params72.7B
Context32K
Smallest23.7 GB
Tool use
NE
nvidia OpenCodeReasoning Nemotron 32B IOI
Nemotron · bartowski
Params32.8B
Context32K
Q4_K_M19.9 GB
CodingReasoning

Other quants

Keep browsing