Loading…
Loading…
Models / Muse-Glimmer
2 models (30B to 30B) · ↓ 398.6K downloads a month · from $0.10/h on RTX 3060 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 |
|---|---|---|---|---|
| Originalmeta-models/Muse-Glimmer-30B | vLLM | 60 GB | 68.9 GB | $0.89/h 2x Nvidia A40 |
| FP8 block (RedHatAI)RedHatAI/Muse-Glimmer-30B-FP8-block | vLLM | 34 GB | 40.9 GB | $0.45/h Nvidia A40 |
| Muse Glimmer NVFP4 (RadixArk)RadixArk/Muse-Glimmer-NVFP4 | vLLM | 20 GB | 24.6 GB | $0.34/h 2x RTX 5060 Ti |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalmeta-models/Muse-Glimmer-30B-assistant | vLLM | 5.1 GB | 8.1 GB | $0.10/h RTX 3060 |
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").