Loading…
Loading…
Models / ultravox-v0_6-qwen-3
GPU memory needed (smallest version of each): ultravox-v0_6-qwen-3 32B about 78.9 GB. The cheapest runs on 2x RTX 4090 from $1.10/h right now.
1 model (32B) · ↓ 36 downloads a month · from $1.10/h on 2x RTX 4090 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 |
|---|---|---|---|---|
| OriginalISTNetworks/ultravox-v0_6-qwen-3-32b-arabic | vLLM | 67 GB | 78.9 GB | $1.10/h 2x RTX 4090 |
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").