Tencent · 80B (13B active) · Mixture of Experts
Reasoning image model — prompt rewrite, chain-of-thought and image-to-image editing Check if your GPU or Mac can run HunyuanImage 3.0 Instruct locally — 30 GB min, 86.4 GB recommended.
2026-014K context
Mixture of Experts
Total experts: 64
Active experts: 8
Active params: 13.0B
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 30 GB | low | — |
| Q3_K_M | 3 | 40.3 GB | moderate | — |
| Q4_K_M | 4 | 45.4 GB | good | — |
| Q5_K_M | 5 | 55.6 GB | good | — |
| Q6_K | 6 | 65.9 GB | excellent | — |
| Q8_0 | 8 | 86.4 GB | excellent | — |
| F16 | 16 | 168.3 GB | lossless | — |
Can I run HunyuanImage 3.0 Instruct locally?
- Can I run HunyuanImage 3.0 Instruct locally?
- HunyuanImage 3.0 Instruct needs about 30 GB of memory at a minimum and 86.4 GB recommended. Open this page to grade it against your GPU or Mac, then run it with runai, Ollama or LM Studio.
- How much VRAM does HunyuanImage 3.0 Instruct need?
- At Q4_K_M, HunyuanImage 3.0 Instruct uses about 45.4 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.