microsoft / automatic-speech-recognition updated 7 months ago

Phi-4-multimodal-instruct

🎉Phi-4: [mini-reasoning reasoning] [multimodal-instruct onnx]; [mini-instruct onnx]

Params
5.6 B
Context
131,072
Downloads 30d
572 K
Likes
1,610
Commercial use: allowed mit Not gated SAFETENSORS 24 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days
572 K539 K
Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors bf16 12.8 GB 15.4 GB ✅ Runs comfortably
model.safetensors (bf16, full) bf16 + 128K ctx 12.8 GB 28.0 GB ❌ Won’t fit
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture
Phi4MMForCausalLM
Parameters
5.6 B
Tensor type
BF16
Context length
131,072
Vocabulary
200,064
Layers / heads
32 / 24
Licence
mit
First seen on the Hub
2025-02-24
Training datasets
undisclosed
Added to our catalog
2026-07-28