LongCat models
4 LongCat models from meituan-longcat on Hugging Face, from 69.1B to 1779.8B parameters, published by meituan-longcat in BF16, with contexts from 128K to 512K tokens. The smallest official model, LongCat-Flash-Lite, needs about 154 GB of VRAM at its published precision; the cheapest live fit is AMD MI300X at $2.63/hr.
Pick a size
One row per official LongCat size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| LongCat-Flash-Lite | 69.1B | 154 GB | 77.2 GB | 38.6 GB | AMD MI300X | $2.63/hr | 0.49 GB |
| LongCat-Flash-Chat | 561.9B | 1256 GB | 628 GB | 314 GB | AMD MI300X × 7 | $18.40/hr | 0.98 GB |
| LongCat-2.5 | 1779.8B | 3978 GB | 1989 GB | 995 GB | No live fit | – | 1.3 GB |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (3)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| LongCat-Flash-Lite | 69.1B | BF16 | 154 GB | AMD MI300X | $2.63/hr |
| LongCat-Flash-Chat | 561.9B | BF16 | 1256 GB | AMD MI300X × 7 | $18.40/hr |
| LongCat-2.5 | 1779.8B | BF16 | 3978 GB | No live fit | – |
Quantized versions (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| LongCat-Flash-Lite-FP8 | 69.1B | F8_E4M3 | 77.2 GB | RTX PRO 6000 | $1.38/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.