What GPU do I need to run state-spaces/mamba-130m-hf?
129M parameters, published in F32. View on Hugging Face
Set up mamba-130m-hfmamba-130m-hf is published by state-spaces on Hugging Face, with 322,130 downloads and 72 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 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run mamba-130m-hf at its published (F32) precision: 1× A16 on vultr, at $0.059/hr per GPU ($0.059/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
mamba-130m-hf: common questions
How much VRAM does mamba-130m-hf need?
0.6 GB at FP32, 0.1 GB at FP8 (quantized), 0.1 GB at INT4 (quantized). All of those sit under 6 GB, the smallest capacity this page reasons about, so VRAM is not what limits where this model runs. The 0.5 GB of weights plus inference overhead is the whole requirement.
Can mamba-130m-hf run in 16-bit instead of FP32?
Yes. Its published weights are FP32, 0.5 GB, or 0.6 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 0.2 GB, or 0.3 GB with overhead. How much accuracy the cast costs is model-specific and is not measured here.
How many copies of mamba-130m-hf fit on one A16?
3, by VRAM alone. That card carries 2.0 GB and one copy needs 0.6 GB at FP32, on a live rate of $0.059/hr for the whole card. Throughput is not modelled here, so 3 copies is not 3 times the requests served.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More state-spaces models
- mamba-2.8b-hf (2.8B, F32)
- mamba-1.4b-hf (1.4B, F32)
- bert-base-uncased (110M, F32)
- Qwen3-0.6B (752M, BF16)
- gpt2 (137M, F32)
- Qwen3-8B (8.2B, BF16)
