Can Hunyuan A13B Instruct run on the H100 PCIe?
Yes. At 8K context the best fit is Q6_K, using about 63.4 GB of the 76.0 GB usable on the H100 PCIe. Estimated speed ceiling: ~187 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|
| 2-bit (Q2_K) • | 28.1 GB Fits | 28.6 GB Fits | 31.6 GB Fits | 427 |
| 3-bit (Q3_K_M) • | 35.9 GB Fits | 36.4 GB Fits | 39.4 GB Fits | 332 |
| 4-bit (Q4_K_M) • | 47.1 GB Fits | 47.6 GB Fits | 50.6 GB Fits | 251 |
| 5-bit (Q5_K_M) • | 54.8 GB Fits | 55.3 GB Fits | 58.3 GB Fits | 215 |
| 6-bit (Q6_K) • | 62.9 GB Fits | 63.4 GB Fits | 66.4 GB Fits | 187 |
| 8-bit (Q8_0) • | 80.7 GB No | 81.2 GB No | 84.2 GB No | — |
| 16-bit (F16/BF16) | 151 GB No | 151 GB No | 154 GB No | — |
• real GGUF file size from bartowski/tencent_Hunyuan-A13B-Instruct-GGUF. Speed is a bandwidth ceiling (2000 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs Hunyuan A13B Instruct: 2x RTX 5090 (2× 32 GB, launch MSRP $3,998) at Q4_K_M, fully in VRAM at 8K context.
- Largest popular model that fits the H100 PCIe: gpt-oss 120B (117B, MoE) at F16, about 61.9 GB at 8K context.
"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.
More
Hunyuan A13B Instruct on every GPU and Mac · Every model that runs on the H100 PCIe · Other models that fit 64 GB VRAM · Try other settings in the calculator
Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs
Data: Hugging Face Hub (tencent/Hunyuan-A13B-Instruct), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.