What GPU do I need to run deepreinforce-ai/Ornith-1.0-397B-FP8?
397.0B parameters, published in F8_E4M3. View on Hugging Face
Set up Ornith-1.0-397B-FP8Ornith-1.0-397B-FP8 is published by deepreinforce-ai on Hugging Face, with 651,672 downloads and 180 likes to date. It's a Qwen3_5MoeForConditionalGeneration model built for text-generation, published natively in F8_E4M3.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run Ornith-1.0-397B-FP8 at its published (F8_E4M3) precision: 5× RTX PRO 6000 on simplepod, at $1.00/hr per GPU ($5.00/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Ornith-1.0-397B-FP8: common questions
Can Ornith-1.0-397B-FP8 run on a single GPU?
No. At FP8 (native) it needs 443.7 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest capable card in the live feed is a 95.0 GB RTX PRO 6000, and it takes 5 of them.
Is Ornith-1.0-397B-FP8 already quantized?
Yes. It is published in FP8, one byte per parameter, so the 443.7 GB figure is already a quantized footprint rather than a full-precision one. Only INT4 goes below it, at 221.8 GB. A GPU without FP8 tensor cores cannot run it as published, which is why cards here are matched on precision support and not on VRAM alone.
How many GPUs do I need to run Ornith-1.0-397B-FP8?
5 at FP8 (native). It needs 443.7 GB of VRAM and the cheapest capable live offer is a 95.0 GB RTX PRO 6000 on simplepod, so 5 of them come to $5.00/hr in total.
Does quantizing Ornith-1.0-397B-FP8 lower the GPU bill?
Yes. At FP8 (native) the cheapest live fit is 5 RTX PRO 6000 cards on simplepod at $5.00/hr. At INT4 (quantized) it drops to 5 RTX 8000 cards on akash at $1.10/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More deepreinforce-ai models
- Ornith-1.0-35B-FP8 (35.1B, F8_E4M3)
- Ornith-1.0-397B (396.8B, BF16)
- bert-base-uncased (110M, F32)
- Qwen3-0.6B (752M, BF16)
- gpt2 (137M, F32)
- Qwen3-8B (8.2B, BF16)
