Loading…
Loading…
Models / Tele-FLM
GPU memory needed (smallest version of each): Tele-FLM about 128.3 GB. The cheapest runs on Nvidia H200 from $4.43/h right now.
1 model · ↓ 16.8K downloads a month · from $4.43/h on Nvidia H200 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 |
|---|---|---|---|---|
| OriginalCofeAI/Tele-FLM | vLLM | 106 GB | 128.3 GB | $4.43/h Nvidia H200 |
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").