What GPU do I need to run meituan-longcat/LongCat-2.5?
1779.8B parameters, published in BF16. View on Hugging Face
LongCat-2.5 is published by meituan-longcat on Hugging Face, with 0 downloads and 34 likes to date. It's a LongcatCausalLM model built for image-text-to-text, published natively in BF16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 3315.0 GB | 3978.1 GB | No capable live offer found | – | – |
| FP8 (quantized) | 1657.5 GB | 1989.0 GB | No capable live offer found | – | – |
| INT4 (quantized) | 828.8 GB | 994.5 GB | AMD MI300X | 6 | $15.77/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
LongCat-2.5: KV cache by context length
The KV cache is the memory the attention layers hold for every token of context, on top of the weights. It is not part of the flat 1.2x overhead in the table above, grows with context length and with every concurrent request, and is why a long-context deployment needs more VRAM than the table shows.
Multi-head latent attention: every layer caches one compressed latent per token. Cached per token: 43,776 bytes at 16-bit.
| Context | KV cache, one sequence |
|---|---|
| 4K | 0.17 GB |
| 32K | 1.3 GB |
| 128K | 5.3 GB |
| 512K (model maximum) | 21.4 GB |
Computed from the layer, head and window counts in the model's own configuration (meituan-longcat/LongCat-2.5), at 16 bits per cached value. Each concurrent sequence needs its own cache, on top of the weights.
LongCat-2.5: common questions
Can LongCat-2.5 run on a single GPU?
Not on a desktop card. At BF16 it needs 3978.1 GB of VRAM, more than a single 32 GB desktop card holds. No card currently listed on the marketplace both supports BF16 and has enough VRAM for it, so how many it would take is not something this page can answer today.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More LongCat models
- LongCat-Flash-Chat (561.9B, BF16)
- LongCat-Flash-Lite-FP8 (69.1B, F8_E4M3)
- LongCat-Flash-Lite (69.1B, BF16)
More on LongCat-2.5
Best vision-language models: how LongCat-2.5 ranks against the rest.
Related reading: H100 pricing and specs, How much VRAM you need for LLMs, Serving LLMs with vLLM, vLLM vs TensorRT-LLM vs SGLang, and Best GPU for LLM inference.
Your own GPU cloud accounts
One console for the GPU clouds you already rent from. Your keys stay on your machine.
$20 a month, flat