Hunyuan-MT-7B-GGUF
I've been experimenting with a new quantization approach that selectively elevates the precision of key layers beyond what the default IMatrix configuration provides.
Params
—
Context
—
Downloads 30d
47 K
Likes
6
Download history
daily snapshots · 89 days
▲ 0 in the last 30 days (0.0%)
47 K47 K
Sep 25Oct 5Oct 15Oct 24
146 K47 K
Jul 28Aug 26Sep 25Oct 24
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| Hunyuan-MT-7B-iq2_xxs.gguf | IQ2_XXS | 2.4 GB | 3.1 GB | ✅ Runs comfortably |
| Hunyuan-MT-7B-iq2_xs.gguf | IQ2_XS | 2.6 GB | 3.4 GB | ✅ Runs comfortably |
| Hunyuan-MT-7B-iq2_s.gguf | IQ2_S | 2.7 GB | 3.5 GB | ✅ Runs comfortably |
| Hunyuan-MT-7B-iq2_m.gguf | IQ2_M | 2.8 GB | 3.6 GB | ✅ Runs comfortably |
| Hunyuan-MT-7B-iq3_xs.gguf | IQ3_XS | 3.3 GB | 4.2 GB | ✅ Runs comfortably |
| Hunyuan-MT-7B-iq3_m.gguf | IQ3_M | 3.7 GB | 4.5 GB | ✅ Runs comfortably |
| Hunyuan-MT-7B-bf16_q8_0.gguf | Q8_0 | 10.9 GB | 12.5 GB | ✅ Runs comfortably |
| Hunyuan-MT-7B-bf16.gguf | GGUF | 15.0 GB | 17.0 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- First seen on the Hub
- 2025-09-05
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Compare with any translation model