All models › meituan
longcat-flash-chat
meituan · MIT license · on Arena since 17 Sept 2025
Download
Arena score1423#109 of 416 in Chat, paid models included
Size561.9 B33.4 B active per token (mixture of experts)
4-bit download341 GBweights only, Q4_K_M
Max context128Ktokens, 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
Arena scores
| Arena | Score | Rank | Votes |
|---|---|---|---|
| Chat | 1423 | #109 of 416 | 11K |
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 | 91 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 | 282 GB | 283 GB | 286 GB | +4.7% noticeable loss |
| Q4_K_M | 341 GB | 342 GB | 345 GB | +1.2% very small loss |
| Q5_K_M | 400 GB | 401 GB | 404 GB | +0.4% near-lossless |
| Q6_K | 462 GB | 462 GB | 466 GB | +0.2% near-lossless |
| Q8_0 | 598 GB | 599 GB | 602 GB | ≈ 0% same as full |
| F16 | 1125 GB | 1125 GB | 1129 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
1400145015001550
MayJunJulAugSeptOct
longcat-flash-chat 1423Best paid model
Arena score from 17 Apr 2026 to 15 Oct 2026.
Similar free models in Chat
- DeepSeek-V3.2 (Thinking) 1424 · 685.4 B
- deepseek-v4-flash-high-preview 1424
- deepseek-v3.2-exp-thinking 1425 · 685.4 B
- Mistral Medium 3.5 1421
- kimi-k2.5-instant 1420
- qwen3-vl-235b-a22b-instruct 1420 · 235.7 B