What GPU do I need to run altomek/YiSM-34B-0rn?
34.4B parameters, published in F16. View on Hugging Face
Set up YiSM-34B-0rnYiSM-34B-0rn is published by altomek on Hugging Face, with 16,795 downloads and 2 likes to date. It's a LlamaForCausalLM model built for text-generation, published natively in F16.
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.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| FP16 | 64.1 GB | 76.9 GB | A100 | 1 | $1.21/hr |
| cheaper alt. | V100 | 5 | $0.440/hr | ||
| FP8 (quantized) | 32.0 GB | 38.4 GB | RTX 4090 | 1 | $0.441/hr |
| cheaper alt. | RTX 5060 Ti | 3 | $0.330/hr | ||
| INT4 (quantized) | 16.0 GB | 19.2 GB | RTX A5000 | 1 | $0.176/hr |
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 YiSM-34B-0rn at its published (F16) precision: 1× A100, at $1.21/hr per GPU ($1.21/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
YiSM-34B-0rn: common questions
Can YiSM-34B-0rn run on a single GPU?
Yes, but not on a desktop card. At FP16 it needs 76.9 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest live single-card fit is a 80.0 GB A100 at $1.21/hr.
What is the least VRAM YiSM-34B-0rn can run in?
19.2 GB, at INT4 (quantized), which fits a 24 GB card, against 76.9 GB at FP16. 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 YiSM-34B-0rn lower the GPU bill?
Yes. At FP16 the cheapest live fit is one A100 at $1.21/hr. At INT4 (quantized) it drops to one RTX A5000 at $0.176/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Yi-1.5 models
- dolphin-2.9.1-yi-1.5-34b (34.4B, BF16)
- Yi-1.5-34B-Chat (34.4B, BF16)
- Yi-1.5-9B-Chat (8.8B, BF16)
- Yi-1.5-9B (8.8B, BF16)
- Yi-1.5-6B (6.1B, BF16)
Related reading: A100 pricing and specs, and The best GPUs for AI, ranked.
