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
GE
Gemma 4 E2B It
Gemma · bartowski
Params4.65B
Context128K
Q4_K_M3.5 GB
Vision
PH
Phi 4 Mini Instruct
Phi · unsloth
Params3.84B
Context128K
Q4_K_M2.5 GB
Coding
GE
Gemma-3-4B-It
Gemma · unsloth
Params3.88B
Context128K
Q4_K_M2.5 GB
Vision
QW
Qwen3 0.6B
Qwen · bartowski
Params752M
Context32K
Q4_K_M0.5 GB
GGUF
MO
MOSS-TTS-v1.5
Moss · christopherthompson81
Params—
Context—
Smallest9.3 GB
GGUF
EM
embeddinggemma-2
Embeddinggemma · ggml-org
Params271M
Context256K
Smallest0.3 GB
EmbeddingVision
QW
Qwen3.5-4B
Qwen · unsloth
Params4.33B
Context256K
Q4_K_M2.8 GB
Vision
DE
Deepseek-R1-Distill-Qwen-1.5B
DeepSeek · unsloth
Params1.78B
Context128K
Q4_K_M1.1 GB
Reasoning
MO
MOSS-TTSD-v1.0
Moss · christopherthompson81
Params—
Context—
Smallest10.2 GB
GGUF
LF
LFM2.5 8B A1B
Lfm · LiquidAI
Params8.47B
Context125K
Q4_K_M5.2 GB
GGUF
GE
Gemma-3-12B-It-Qat
Gemma · unsloth
Params11.8B
Context128K
Q4_K_M7.3 GB
Vision
LF
LFM2.5-350M
Lfm · LiquidAI
Params354M
Context125K
Q4_K_M0.2 GB
GGUF
QW
Qwen3.8 Flash Next
Qwen · bartowski
Params177B
Context256K
Q4_K_M119.6 GB
Vision
VI
VibeVoice-ASR-Streaming-7B
Vibevoice · audio-cpp
Params7B
Context—
Smallest5.9 GB
GGUF
QW
Swift 1.5 Qwen3.8 27B Uncensored Dynamic MTP
Qwen · ajgazin
Params28B
Context256K
Smallest8.8 GB
Vision
GE
Gemma 4 E4B It Ultra Uncensored Heretic
Gemma · llmfan46
Params7.5B
Context128K
Q4_K_M5.3 GB
Vision
QW
Qwen3-Vl-2B-Instruct
Qwen · unsloth
Params1.72B
Context256K
Q4_K_M1.1 GB
Vision
QW
Qwen3.8 27B Humanlike Chat
Qwen · LessThanThreeAI
Params26.9B
Context256K
Q4_K_M16.6 GB
ReasoningRoleplayTool use
NE
NVIDIA Nemotron 3.5 Bolt E4B
Nemotron · unsloth
Params7.52B
Context128K
Smallest0.0 GB
GGUF
VI
VibeVoice ASR Streaming 1.5B
Vibevoice · christopherthompson81
Params3.1B
Context—
Smallest2.1 GB
GGUF
FL
FLUX.2 dev
Flux · unsloth
Params32.2B
Context—
Q4_K_M20.0 GB
GGUF
FL
FLUX.2 klein base 9B
Flux · unsloth
Params9.08B
Context—
Q4_K_M5.9 GB
GGUF
QW
Qwen3.6-27B
Qwen · ggml-org
Params26.9B
Context256K
Q4_K_M19.1 GB
Vision
HE
Hermes 4 14B
Hermes · bartowski
Params14.8B
Context40K
Q4_K_M9.0 GB
Tool use
MI
Devstral-Small-2-24B-Instruct-2512
Mistral · unsloth
Params23.6B
Context384K
Q4_K_M14.3 GB
CodingVision
QW
Qwen3.5-9B
Qwen · unsloth
Params9.2B
Context256K
Q4_K_M5.9 GB
Vision
QW
Qwen3.6 35B A3B Uncensored Heretic Native MTP Preserved
Qwen · llmfan46
Params35.5B
Context256K
Q4_K_M21.8 GB
Vision
GE
Gemma 4 31B It Uncensored Heretic
Gemma · llmfan46
Params30.7B
Context256K
Q4_K_M18.7 GB
Vision
NA
Nanbeige4.3 33B
Nanbeige · bartowski
Params33.1B
Context512K
Q4_K_M20.8 GB
ReasoningTool use
CL
Clef-Flash
Clef · ggml-org
Params9.08B
Context256K
Q4_K_M6.7 GB
ReasoningTool useVision

Other quants

Keep browsing