tencent
Hy MT2 1.8B
Hy MT2 1.8B is a 1.79B dense hunyuan-dense model from tencent. Configured context length is 262,144 tokens. License: apache-2.0. Quant sizes are the GGUF file bytes published on Hugging Face when a file exists.
Parameters1.8B
Context256K
Attentiongqa
Licenseapache-2.0
32 layers · 4 KV heads · head dim 128 · GGUF repo · config
Quant file sizes
| Quant | File size | Source |
|---|---|---|
| Q8_0 | 1.78 GB | Hugging Face file bytes |
| Q6_K | 1.37 GB | Hugging Face file bytes |
| Q4_K_M | 1.06 GB | Hugging Face file bytes |
On common machines
| Device | Verdict | Quant | Speed |
|---|---|---|---|
| GeForce RTX 4060 Ti 8GB | Runs great | Q8_0 | 65–88 |
| GeForce RTX 3060 12GB | Runs great | Q8_0 | 81–110 |
| GeForce RTX 4060 Ti 16GB | Runs great | Q8_0 | 65–88 |
| GeForce RTX 4090 | Runs great | Q8_0 | 227–309 |
| GeForce RTX 5090 | Runs great | Q8_0 | 403–550 |
| Apple M4 Pro | Runs great | Q8_0 | 61–84 |
| Apple M5 | Runs great | Q8_0 | 34–47 |
| CPU only · DDR5-5600 | Runs on CPU | Q8_0 | 20–27 |
Smallest devices that fit it fully
- GeForce RTX 3050 6GB — Runs great, Q8_0, 38–52 tok/s
- GeForce RTX 2060 6GB — Runs great, Q8_0, 76–103 tok/s
- GeForce GTX 1660 Super — Runs great, Q8_0, 76–103 tok/s
- GeForce GTX 1660 Ti — Runs great, Q8_0, 65–88 tok/s
- Intel Arc A380 — Runs great, Q8_0, 42–57 tok/s
- GeForce RTX 5060 Ti 8GB — Runs great, Q8_0, 101–137 tok/s
Run it
Commands for the GeForce RTX 4060 Ti 16GB estimate (Q8_0).
llama.cpp
llama-server -hf tencent/Hy-MT2-1.8B-GGUF:Q8_0 -c 8192 -ngl 32
No matching name in the Ollama library snapshot.
LM Studio
lms get tencent/Hy-MT2-1.8B-GGUF # Then load quant Q8_0