Hy MT2 1.8B — Hardware Requirements & GPU Compatibility
Translation
Hy MT2 1.8B is a 2-billion-parameter translation model from Tencent's Hunyuan team, part of a three-size Hy-MT2 family (1.8B, 7B, and a 30B mixture-of-experts variant) built specifically for machine translation rather than general chat. It supports translation across roughly three dozen languages and follows translation-specific instructions, such as adjusting tone or terminology. It runs on modest consumer hardware, including laptops, and Tencent has also released extreme-quantized versions shrunk to a few hundred megabytes for on-device use. It supports a 262K token context window, letting it translate long documents in a single pass. It is released under the Apache 2.0 license, allowing unrestricted commercial and research use. Published in May 2026, it is the smallest member of a translation-focused family Tencent positions as a self-hostable alternative to commercial translation APIs.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 64K)Best on 24 GB (Q4_K_M · ~395 tok/s · 256K)Macs from 8 GB (Q4_K_M · ~43 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Hy MT2 1.8B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run hf.co/tencent/Hy-MT2-1.8B-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 21.4 GB free · 16K context
Download: Hy-MT2-1.8B-Q4_K_M.gguf1.13 GBtencent
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (9 GB headroom) · Q4_K_M
- Generation speed
- ~141 tok/s
- generation speed
- Cost per 1M output tokens
- $0.14
- per 1M output tokens
How Much VRAM Does Hy MT2 1.8B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.3 GB | 3.3 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 256K context · ~504 tok/s | |
| 1.3 GB | 3.3 GB | 3-bit small — 3-bit small quantization | Fits: 256K context · ~493 tok/s | |
| 1.4 GB | 3.4 GB | 3-bit medium — 3-bit medium quantization | Fits: 256K context · ~458 tok/s | |
| 1.4 GB | 3.5 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 256K context · ~452 tok/s | |
| 1.7 GB | 3.7 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 256K context · ~395 tok/s | |
| 1.9 GB | 3.9 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 256K context · ~347 tok/s | |
| 2.1 GB | 4.1 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 256K context · ~309 tok/s | |
| 2.5 GB | 4.5 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 256K context · ~265 tok/s |
Selected Q4_K_M
4-bit medium quantization2.6GBat 16K context
- Weights
- 1.2 GB
- KV cache
- 1.1 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 21.4 GB free · ~395 tok/s
≥50 tok/s needs ≥128 GB/s · RTX 5090 ~702, RTX 3090 Ti ~395
Which Hardware Can Run Hy MT2 1.8B?
Q4_K_M · 1.7 GBHy MT2 1.8B (Q4_K_M) requires 1.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. Using the full 262K context window can add up to 17.0 GB, bringing total usage to 18.7 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Hy MT2 1.8B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 5.4 GB free · up to 64K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~298Simulate output on RTX 3080RTX 2080 Ti~241Simulate output on RTX 2080 TiRTX 3070 Ti~238Simulate output on RTX 3070 TiM3*8 GB~43Simulate output on iMac 24" M3 (8 GB)Orin Nano~40Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~29Simulate output on iPhone 1720 GB
fits · 17.4 GB free · up to 256K ctx
1 GPU
RX 7900 XT~289Simulate output on RX 7900 XT32–40 GB
fits · 29.4 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~702Simulate output on RTX 5090M5 Max36 GB~194Simulate output on Mac Studio M5 Max (36 GB)M532 GB~65Simulate output on MacBook Air 13" M5 (32 GB)Orin~80Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~53Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Hy MT2 1.8B
Hunyuan MT2 family · 3 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3 VL 2B InstructAlibaba | — | 3.5 GB | ~362 | same size |
| Moondream2vikhyatk | — | 3 GB | ~516 | same size |
| OneRec 1.7BOpenOneRec | — | 3.5 GB | ~362 | same size |
| Gemma 3n E2B IT Litert LmGoogle | — | 3.1 GB | ~496 | same size |
| Helium 1 2Bkyutai | — | 2 GB | ~374 | same size |
| H2ovl Mississippi 2Bh2oai | — | 6.5 GB | ~138 | same size |
Specifications
- Publisher
- Tencent
- Family
- Hunyuan MT2
- Parameters
- 2.0B
- Architecture
- HunYuanDenseV1ForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 120,818
- Release Date
- 2026-05-11
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Hy MT2 1.8B need?
Hy MT2 1.8B requires 1.7 GB of VRAM at Q4_K_M, or 4.5 GB at BF16. Full 262K context adds up to 17.0 GB (18.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 2.0B × 4.8 bits ÷ 8 = 1.2 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 17.5 GB (at full 262K context)
VRAM usage by quantization
What's the best quantization for Hy MT2 1.8B?
For Hy MT2 1.8B, Q4_K_M (1.7 GB) offers the best balance of quality and VRAM usage. Q5_K_S (1.8 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 1.0 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Hy MT2 1.8B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Hy MT2 1.8B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.7 GB of usable unified memory (RAM minus macOS overhead).
Can I run Hy MT2 1.8B locally?
Yes — Hy MT2 1.8B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Hy MT2 1.8B?
At Q4_K_M, Hy MT2 1.8B can reach ~2892 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~395 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 ÷ 1.66 × 0.65 = ~3133 tok/s
Estimated speed at Q4_K_M (1.7 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Hy MT2 1.8B?
At Q4_K_M, the download is about 1.22 GB. The full-precision BF16 version is 4.08 GB. The smallest option (IQ2_XXS) is 0.56 GB.
Which GPUs can run Hy MT2 1.8B?
52 consumer GPUs can run Hy MT2 1.8B at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Hy MT2 1.8B?
163 devices with unified memory can run Hy MT2 1.8B at Q4_K_M (1.7 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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.