All models › inclusionAI
Ling-3.1-flash
inclusionAI · on Arena since 13 Oct 2026
Download New · waiting for Arena votes
Arena score—Not voted on Arena yet
Size572.1 B33.1 B active per token (mixture of experts)
4-bit download347 GBweights only, Q4_K_M
Max context256Ktokens, from the model config
Where to use it for free
- Download and run it at home: official weights · GGUF files for Ollama and LM Studio
New: waiting for Arena votes
Released on 13 Oct 2026. Arena has not voted on this model yet. As soon as it does, the model moves into the ranking automatically, usually the next night. Until then you can still check its size, memory needs and speed below.
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 | 85 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 | 287 GB | 289 GB | 298 GB | +4.7% noticeable loss |
| Q4_K_M | 348 GB | 350 GB | 358 GB | +1.2% very small loss |
| Q5_K_M | 408 GB | 410 GB | 418 GB | +0.4% near-lossless |
| Q6_K | 470 GB | 472 GB | 481 GB | +0.2% near-lossless |
| Q8_0 | 609 GB | 611 GB | 619 GB | ≈ 0% same as full |
| F16 | 1145 GB | 1148 GB | 1156 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.