dots3-note-prev NVFP4

hero

167G mixed NVFP4 of dots-studio/dots3-note-prev (280B / 16B active MoE, Apache-2.0).
Experts → NVFP4. MLA / DSA / MTP / vision / audio stay FP8 or BF16. No REAP.

vLLM 0.27+ · Dots3NoteForCausalLM · --language-model-only if you only want text.

Benches (upstream)

Quality numbers are from dots-studio, not this quant.

reasoning

multimodal

Files

133 shards + vision + audio. compressed-tensors / nvfp4-pack-quantized on routed+shared experts.

hf download Frosty40/dots3-note-prev-NVFP4
Downloads last month
-
Safetensors
Model size
152B params
Tensor type
BF16
·
F32
·
F8_E4M3
·
U8
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Frosty40/dots3-note-prev-NVFP4

Quantized
(1)
this model