What GPU do I need to run state-spaces/mamba-2.8b-hf?
2.8B parameters, published in F32. View on Hugging Face
mamba-2.8b-hf is published by state-spaces on Hugging Face, with 18,823 downloads and 123 likes to date. It's a MambaForCausalLM model built for text-generation, published natively in F32.
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 caveat: requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run mamba-2.8b-hf at its published (F32) precision: 1× RTX 5060 Ti on simplepod, at $0.100/hr per GPU ($0.100/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More state-spaces models
- mamba-130m-hf (129M, F32)
- mamba-1.4b-hf (1.4B, F32)
- Qwen3-0.6B (752M, BF16)
- gpt2 (137M, F32)
- Qwen3-8B (8.2B, BF16)
- Qwen3.6-35B-A3B-FP8 (36.0B, F8_E4M3)
