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
LFM2.5 8B A1B
Qwen · zugquants
Params8.47B
Context125K
Smallest4.6 GB
ReasoningTool use
QW
Qwen3.5 9B Nikusui v1 Uncensored Heretic
Qwen · llmfan46
Params9.2B
Context256K
Q4_K_M6.4 GB
Vision
FA
Fara1.5 9B
Fara · prithivMLmods
Params8.95B
Context256K
Q4_K_M5.6 GB
Vision
LU
Menlo Lucy
Lucy · bartowski
Params1.72B
Context40K
Q4_K_M1.1 GB
GGUF
NE
Nemomix v2.0 12B
Nemomix · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
QW
Qwen3.6 29B REAP Opus Reasoning Distill MTP
Qwen · barozp
Params28.9B
Context256K
Q4_K_M17.7 GB
ReasoningTool use
LF
LFM3 Omni 2B
Lfm · erenyeager-1
Params1.73B
Context125K
Q4_K_M1.1 GB
ReasoningTool useVision
GE
Gemma4 31b Gembrain Equinox
Gemma · bartowski
Params30.7B
Context256K
Q4_K_M19.6 GB
Roleplay
FA
Falcon H1 3B Instruct
Falcon · tiiuae
Params3.15B
Context128K
Q4_K_M1.9 GB
GGUF
CO
Yi Coder 9B Chat
Coder · legraphista
Params8.83B
Context128K
Smallest2.0 GB
Coding
OL
Olmo 3 7B Think
OLMo · bartowski
Params7.3B
Context64K
Q4_K_M4.5 GB
Reasoning
NE
NVIDIA Nemotron 3 Super 120B A12B BF16 heretic v2
Nemotron · Sabomako
Params121B
Context1024K
Smallest68.6 GB
ReasoningTool use
DE
DeepSeek V4 Flash DSpark draft
DeepSeek · YanissAmz
Params19.8B
Context—
Smallest10.9 GB
GGUF
LO
LongCat Flash Lite Sparse Uncensored Heretic Native MTP And LSA Preserved
Longcat · llmfan46
Params69B
Context960K
Q4_K_M41.2 GB
GGUF
IN
Internvl3-14B-Instruct
Internvl · unsloth
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingVision
SA
Sarvam M
Sarvam · bartowski
Params23.6B
Context32K
Q4_K_M14.3 GB
Reasoning
GE
gemma-4-E2B
Gemma · ggml-org
Params4.65B
Context128K
Smallest5.0 GB
GGUF
GE
Gemma 4 26B A4B It
Gemma · giladgd
Params25.2B
Context256K
Q4_K_M16.8 GB
Vision
NE
NemoAurora RP 12B
Nemoaurora · Aratako
Params12.2B
Context1000K
Q4_K_M7.5 GB
Roleplay
OP
OpenThinker Agent v1
Openthinker · bartowski
Params8.2B
Context40K
Q4_K_M5.0 GB
Coding
LU
Lucy 128k
Lucy · bartowski
Params1.72B
Context128K
Q4_K_M1.1 GB
GGUF
QW
Qwen3.8 23B Mini Me Bf16
Qwen · torchsnow
Params22.3B
Context256K
Smallest11.1 GB
Vision
PH
dolphin-2.9.2-Phi-3-Medium-abliterated
Phi · legraphista
Params14B
Context4K
Smallest3.1 GB
CodingTool use
QW
Qwen2.5-VL-72B-Instruct
Qwen · Mungert
Params73B
Context125K
Q4_K_M47.7 GB
Vision
IN
Internvl3-1B-Instruct
Internvl · unsloth
Params630M
Context32K
Q4_K_M0.5 GB
CodingVision
SP
Spark X2.6 1.7B i
Spark · maternion
Params1.71B
Context1024K
Q4_K_M1.1 GB
ReasoningTool use
PH
Phi 3 mini 3.8b 4Bit InstructionTuned Alpaca
Phi · Chituyi
Params3.82B
Context4K
Q4_K_M2.3 GB
GGUF
NE
neo_7b_sft_v0.1
Neo · legraphista
Params7.79B
Context8K
Smallest1.7 GB
GGUF
ST
HOT Step CPP StableStep
Stable · scragnog
Params1.45B
Context—
Q4_K_M0.8 GB
GGUF
LL
UserLM-8b
Llama · Mungert
Params8.03B
Context8K
Q4_K_M5.3 GB
GGUF

Other quants

Keep browsing