What GPU do I need to run deepreinforce-ai/Ornith-1.0-35B-FP8?
35.1B parameters, published in F8_E4M3. View on Hugging Face
Set up Ornith-1.0-35B-FP8Ornith-1.0-35B-FP8 is published by deepreinforce-ai on Hugging Face, with 930,696 downloads and 78 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-1.0-35B-FP8 at its published (F8_E4M3) precision: 1× RTX 4090 on vastai, at $0.589/hr per GPU ($0.589/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Ornith-1.0-35B-FP8: common questions
Can Ornith-1.0-35B-FP8 run on a single GPU?
Yes, but not on a desktop card. At FP8 (native) it needs 39.3 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest live single-card fit is a 48.0 GB RTX 4090 on vastai at $0.589/hr.
Is Ornith-1.0-35B-FP8 already quantized?
Yes. It is published in FP8, one byte per parameter, so the 39.3 GB figure is already a quantized footprint rather than a full-precision one. Only INT4 goes below it, at 19.6 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.
What is the least VRAM Ornith-1.0-35B-FP8 can run in?
19.6 GB, at INT4 (quantized), which fits a 24 GB card, against 39.3 GB at FP8 (native). That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Does quantizing Ornith-1.0-35B-FP8 lower the GPU bill?
Yes. At FP8 (native) the cheapest live fit is one RTX 4090 on vastai at $0.589/hr. At INT4 (quantized) it drops to one RTX A5000 on runpod at $0.160/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-1.0-397B-FP8 (397.0B, 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)
