moonshotai models
1 moonshotai model from Moonshot AI on Hugging Face, from 49.1B to 49.1B parameters, published by Moonshot AI in BF16, with a 1M-token context. The smallest official model, Kimi-Linear-48B-A3B-Instruct, needs about 110 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 moonshotai 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 |
|---|---|---|---|---|---|---|---|
| Kimi-Linear-48B-A3B-Instruct | 49.1B | 110 GB | 54.9 GB | 27.4 GB | AMD MI300X | $2.63/hr | 0.95 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 (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Kimi-Linear-48B-A3B-Instruct | 49.1B | BF16 | 110 GB | AMD MI300X | $2.63/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.