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
MI
MiniCPM5 2B Abliterated
MiniCPM · SC117
Params2.52B
Context128K
Q4_K_M1.6 GB
GGUF
PO
Polaris 7B Preview
Polaris · bartowski
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF
QW
Qwen3.5-4B
Qwen · Heppygaga
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
LI
Ling Lite 0415
Ling · bartowski
Params16.8B
Context32K
Q4_K_M11.2 GB
GGUF
EM
Embeddinggemma 2
Embeddinggemma · prithivMLmods
Params271M
Context256K
Q4_K_M0.2 GB
EmbeddingVision
LL
Llama 3.1 Minitron 4B Width Base
Llama · legraphista
Params4.51B
Context128K
Smallest1.8 GB
GGUF
LL
DarkIdol Llama 3.1 8B Instruct 1.1 Uncensored
Llama · LWDCLS
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
HE
Hearthfire 24B
Hearthfire · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
FA
Falcon-H1-1.5B-Instruct
Falcon · unsloth
Params1.55B
Context128K
Q4_K_M0.9 GB
GGUF
QW
Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive
Qwen · Unrestricted
Params34.7B
Context256K
Q4_K_M21.2 GB
Vision
LL
Llama 3.3 8B Instruct 128K_Abliterated
Llama · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
GE
Gemma 4 E4B It
Gemma · prithivMLmods
Params7.5B
Context128K
Q4_K_M5.3 GB
Vision
QW
Qwen3 8B RP v0.1
Qwen · Aratako
Params8.19B
Context40K
Q4_K_M5.0 GB
Roleplay
MI
Mistral Small 3.2 24B Instruct 2506 Heretic v1.2 2
Mistral · grayarea
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
DE
DeepSeek V4.1 Flash 1017 IQ2 XXS
DeepSeek · smalinin
Params748B
Context1024K
Smallest8.5 GB
GGUF
QW
Qwen3.5-4B
Qwen · Limeboi
Params4.21B
Context256K
Q4_K_M2.7 GB
Vision
QW
Qwen3-Coder-480B-A35B-Instruct-1M
Qwen · unsloth
Params480B
Context1024K
Q4_K_M290.1 GB
Coding
QW
Qwen3-Vl-235B-A22B-Thinking-1M
Qwen · unsloth
Params235B
Context977K
Q4_K_M142.2 GB
ReasoningVision
TA
Talkie 1930 13b It Hf
Talkie · niklassheth
Params13.3B
Context2K
Q4_K_M8.5 GB
GGUF
LL
Llama 3.1 SuperNova Lite
Llama · legraphista
Params8B
Context128K
Smallest2.0 GB
GGUF
QW
Qwen3-Vl-32B-Thinking-1M
Qwen · unsloth
Params32.8B
Context977K
Q4_K_M19.8 GB
ReasoningVision
QW
Huihui-Qwen3.5-9B-abliterated
Qwen · Mungert
Params8.95B
Context256K
Q4_K_M6.0 GB
ReasoningTool use
GL
GLM-4.7-Flash
GLM · Mungert
Params30B
Context198K
Q4_K_M18.5 GB
GGUF
TE
Tessa T1 32B
Tessa · bartowski
Params32.8B
Context117K
Q4_K_M19.9 GB
GGUF
OL
Olmo 3 32B Think
OLMo · bartowski
Params32.2B
Context64K
Q4_K_M19.5 GB
Reasoning
FL
flint roleplay antislop
Flint · rawmodels
Params39.8B
Context256K
Q4_K_M25.3 GB
Roleplay
QW
MiMo V2.6 Distill Qwen 9B
Qwen · ldov
Params8.95B
Context256K
Q4_K_M5.8 GB
CodingTool useVision
QW
Qwen3.5-4B
Qwen · mistaplanet
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
GL
Remnant Glm4 32b
GLM · bartowski
Params32.6B
Context32K
Q4_K_M19.7 GB
Roleplay
IS
Ising Calibration 1.5 31B
Ising · bartowski
Params30.7B
Context256K
Q4_K_M19.6 GB
Vision

Other quants

Keep browsing