Runs on Data centre · Hugging Face ↗
Coding index 58.8 (Artificial Analysis)
Tencent Hunyuan's ~299B MoE, open-weight — the same model whose hosted free window opened and closed on the leaderboard, here as a self-host option.
Real GGUF file sizes = weight VRAM. Add the KV cache for your context (≈11 GB at 32K, fp16).
| Quantization | Size |
|---|---|
| Q3_K_M | 137.5 GB |
| IQ4_XS | 160.8 GB |
| Q4_0 | 170.3 GB |
| Q4_K_S | 175.5 GB |
| Q4_K_M | 182.2 GB |
| Q4 | 182.5 GB |
| Q4_1 | 187.8 GB |
| Q5_K_M | 212.8 GB |
| Q2_K | 213.9 GB |
| Q6_K | 257.2 GB |
| Q8_0 | 317.7 GB |
~182 GB at Q4 — multi-GPU. A GGUF exists, so llama.cpp with heavy offload is possible but slow; vLLM / SGLang tensor-parallel is the real route.