Hermes 3 models
3 Hermes 3 models from Nous Research on Hugging Face, from 8.0B to 405.9B parameters, published by Nous Research in BF16, with a 128K-token context. The smallest official model, Hermes-3-Llama-3.1-8B, needs about 17.9 GB of VRAM at its published precision; the cheapest live fit is RTX A5000 at $0.176/hr.
Pick a size
One row per official Hermes 3 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 |
|---|---|---|---|---|---|---|---|
| Hermes-3-Llama-3.1-8B | 8.0B | 17.9 GB | 9.0 GB | 4.5 GB | RTX A5000 | $0.176/hr | 4.0 GB |
| Hermes-3-Llama-3.1-70B | 70.6B | 158 GB | 78.8 GB | 39.4 GB | AMD MI300X | $2.63/hr | 10.0 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 (2)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Hermes-3-Llama-3.1-8B | 8.0B | BF16 | 17.9 GB | RTX A5000 | $0.176/hr |
| Hermes-3-Llama-3.1-70B | 70.6B | BF16 | 158 GB | AMD MI300X | $2.63/hr |
Quantized versions (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Hermes-3-Llama-3.1-405B-FP8 | 405.9B | F8_E4M3 | 454 GB | RTX PRO 6000 × 5 | $6.88/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.
More from Nous Research
- Hermes 2 (4 models)