Axion1-0 models
1 Axion1-0 model from Axion1-0 on Hugging Face, from 35.1B to 35.1B parameters, published by Axion1-0 in BF16, with a 256K-token context. The smallest official model, Axion-1.0-35B, needs about 78.5 GB of VRAM at its published precision; the cheapest live fit is RTX PRO 6000 at $1.38/hr.
Pick a size
One row per official Axion1-0 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 |
|---|---|---|---|---|---|---|---|
| Axion-1.0-35B | 35.1B | 78.5 GB | 39.2 GB | 19.6 GB | RTX PRO 6000 | $1.38/hr | 0.63 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 (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Axion-1.0-35B | 35.1B | BF16 | 78.5 GB | RTX PRO 6000 | $1.38/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.
