All models › tencent
Arena score1438#80 of 416 in Chat, paid models included
Size298.8 B24.4 B active per token (mixture of experts)
4-bit download181 GBweights only, Q4_K_M
Max context256Ktokens, from the model config
Where to use it for free
- The lab's own chat: yuanbao.tencent.com (free with daily limits)
- Download and run it at home: official weights · GGUF files for Ollama and LM Studio
Arena scores
Rank among all models, paid ones included. Source: Arena leaderboard dataset.
Speed on popular hardware
| Hardware | GPU memory | Fits? | Speed |
|---|---|---|---|
| RTX 3060 12 GB | 12 GB | Does not fit | — |
| RTX 4060 Ti 16 GB | 16 GB | Does not fit | — |
| RTX 3090 | 24 GB | Does not fit | — |
| RTX 4090 | 24 GB | Does not fit | — |
| RTX 5090 | 32 GB | Does not fit | — |
| RX 7900 XTX | 24 GB | Does not fit | — |
| 2 × RTX 3090 | 48 GB | Does not fit | — |
| 4 × RTX 3090 | 96 GB | Does not fit | — |
| Mac M4 Max 128 GB | 96 GB | Does not fit | — |
| Ryzen AI Max+ 395 128 GB | 96 GB | Does not fit | — |
| 8 × H100 SXM | 640 GB | Fits in GPU | 76 tok/s |
Estimate at 4-bit with 32K context, 64 GB of DDR5 for offload. Speed ≈ memory bandwidth × 70% ÷ data read per token; real numbers vary by about ±30%.
GPU memory needed
| Level | 8K context | 32K context | 128K context | Quality vs full |
|---|---|---|---|---|
| Q3_K_M | 153 GB | 161 GB | 193 GB | +4.7% noticeable loss |
| Q4_K_M | 184 GB | 192 GB | 225 GB | +1.2% very small loss |
| Q5_K_M | 216 GB | 224 GB | 256 GB | +0.4% near-lossless |
| Q6_K | 248 GB | 256 GB | 289 GB | +0.2% near-lossless |
| Q8_0 | 321 GB | 329 GB | 361 GB | ≈ 0% same as full |
| F16 | 601 GB | 609 GB | 641 GB | ≈ 0% same as full |
Weights + context cache (from the model's architecture) + runtime. Quality: increase in perplexity against the full model, from llama.cpp tests, scaled by model size. Simulate your own setup.
Chat score over time
145015001550
MayJunJulAugSeptOct
Hy3 1438Best paid model
Arena score from 17 Apr 2026 to 15 Oct 2026.
Similar free models in Chat
- Qwen3.5-397B-A17B 1438 · 403.4 B
- GLM-4.6 1440 · 356.8 B
- Inkling 1441
- Qwen3.8-27B 1441 · 27.8 B
- GLM-4.7 1435 · 358.3 B
- Gemma 4 26B A4B 1434 · 25.8 B