Hy MT2 30B A3B — Hardware Requirements & GPU Compatibility
Translation
Hy-MT2-30B-A3B is Tencent's largest "fast-thinking" multilingual translation model in the Hy-MT2 family, alongside smaller 1.8B and 7B siblings, built specifically for translation rather than general chat and tuned to follow translation instructions across 33 languages. It is a mixture-of-experts model with roughly 30 billion total and 3.5 billion active parameters per token, and Tencent reports it beating open models such as DeepSeek-V4-Pro and Kimi K2.6 on translation quality in fast-thinking mode. The release also ships an FP8-quantized checkpoint, and the smaller 1.8B sibling gets extreme sub-2-bit GGUF quantizations for on-device use. With roughly 3.5 billion active parameters, the 30B-A3B checkpoint is light enough to run on a single consumer GPU once quantized. Context length is 262,144 tokens. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in May 2026, alongside the smaller Hy-MT2-1.8B and Hy-MT2-7B models and the IFMTBench translation-instruction benchmark.
23.0K downloads
501 likesSpecifications
- Publisher
- Tencent
- Family
- Hunyuan MT2
- Parameters
- 30.1B
- Architecture
- HYV3ForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 120,832
- Release Date
- 2026-05-11
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Hy MT2 30B A3B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 13.2 GB | 26.0 GB | 12.78 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 13.6 GB | 26.3 GB | 13.15 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 15.1 GB | 27.8 GB | 14.66 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 18.4 GB | 31.2 GB | 18.04 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 21.8 GB | 34.6 GB | 21.42 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 25.2 GB | 38.0 GB | 24.80 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 30.5 GB | 43.3 GB | 30.06 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Hy MT2 30B A3B?
Q4_K_M · 18.4 GBHy MT2 30B A3B (Q4_K_M) requires 18.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 24+ GB is recommended. Using the full 262K context window can add up to 12.8 GB, bringing total usage to 31.2 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Hy MT2 30B A3B?
Q4_K_M · 18.4 GB41 devices with unified memory can run Hy MT2 30B A3B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download Hy MT2 30B A3B
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does Hy MT2 30B A3B need?
Hy MT2 30B A3B requires 18.4 GB of VRAM at Q4_K_M, or 60.5 GB at BF16. Full 262K context adds up to 12.8 GB (31.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 30.1B × 4.8 bits ÷ 8 = 18 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 13.2 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M18.4 GBQ4_K_M + full context31.2 GB- Can NVIDIA GeForce RTX 4090 run Hy MT2 30B A3B?
Yes, at Q5_K_M (21.8 GB) or lower. Higher quantizations like Q6_K (25.2 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Hy MT2 30B A3B?
For Hy MT2 30B A3B, Q4_K_M (18.4 GB) offers the best balance of quality and VRAM usage. Q5_K_S (21.1 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 13.2 GB.
VRAM requirement by quantization
Q2_K13.2 GBQ3_K_L15.8 GBQ4_K_M ★18.4 GBQ5_K_S21.1 GBQ5_K_M21.8 GBBF1660.5 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Hy MT2 30B A3B on a Mac?
Hy MT2 30B A3B requires at least 13.2 GB at Q2_K, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Hy MT2 30B A3B locally?
Yes — Hy MT2 30B A3B can run locally on consumer hardware. At Q4_K_M quantization it needs 18.4 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Hy MT2 30B A3B?
At Q4_K_M, Hy MT2 30B A3B can reach ~100 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~170 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 18.4 × 0.65 = ~328 tok/s
Estimated speed at Q4_K_M (18.4 GB)
~328 tok/s~170 tok/s~328 tok/s~303 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Hy MT2 30B A3B?
At Q4_K_M, the download is about 18.04 GB. The full-precision BF16 version is 60.13 GB. The smallest option (Q2_K) is 12.78 GB.
- Which GPUs can run Hy MT2 30B A3B?
8 consumer GPUs can run Hy MT2 30B A3B at Q4_K_M (18.4 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run Hy MT2 30B A3B?
41 devices with unified memory can run Hy MT2 30B A3B at Q4_K_M (18.4 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.