Loading…
Loading…
Models / granite-speech-3.2
GPU memory needed (smallest version of each): granite-speech-3.2 8B about 22.4 GB. The cheapest runs on RTX 3090 Ti from $0.28/h right now.
1 model (8B) · ↓ 34.4K downloads a month · from $0.28/h on RTX 3090 Ti right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalibm-granite/granite-speech-3.2-8b | vLLM | 17 GB | 22.4 GB | $0.28/h RTX 3090 Ti |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").