tencent / translation updated 2 weeks ago

Hy-MT2-30B-A3B

🖥️ Official Website     💬 GitHub     🪡 AngelSlim     📚 Hy-MT2 Report

Params
30.1 B
Context
262,144
Downloads 30d
95 K
Likes
485
Commercial use: allowed apache-2.0 Not gated SAFETENSORS 36 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days
187 K95 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 60.1 GB 71.2 GB ❌ Won’t fit
model.safetensors (bf16, full) bf16 + 256K ctx 60.1 GB 210.9 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
HYV3ForCausalLM
Parameters
30.1 B
Tensor type
BF16
Context length
262,144
Vocabulary
120,832
Layers / heads
48 / 32
Licence
apache-2.0
First seen on the Hub
2026-05-11
Training datasets
undisclosed
Added to our catalog
2026-07-28