What GPU do I need to run cais/HarmBench-Llama-2-13b-cls?
13.0B parameters, published in BF16. View on Hugging Face
Set up HarmBench-Llama-2-13b-clsHarmBench-Llama-2-13b-cls is published by cais on Hugging Face, with 142,528 downloads and 32 likes to date. It's a LlamaForCausalLM model built for text-generation, published natively in BF16.
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) |
|---|---|---|---|---|---|
| BF16 | 24.2 GB | 29.1 GB | RTX 4080 Super | 1 | $0.338/hr |
| cheaper alt. | RTX 3060 | 3 | $0.330/hr | ||
| FP8 (quantized) | 12.1 GB | 14.5 GB | RTX 5060 Ti | 1 | $0.188/hr |
| INT4 (quantized) | 6.1 GB | 7.3 GB | RTX 3060 | 1 | $0.110/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 HarmBench-Llama-2-13b-cls at its published (BF16) precision: 1× RTX 4080 Super, at $0.338/hr per GPU ($0.338/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
HarmBench-Llama-2-13b-cls: common questions
Does HarmBench-Llama-2-13b-cls fit on a 32 GB GPU?
Yes. At BF16 it needs 29.1 GB of VRAM, so a 32 GB card holds it with 2.9 GB to spare. A 24 GB card is not enough for it at BF16.
What is the least VRAM HarmBench-Llama-2-13b-cls can run in?
7.3 GB, at INT4 (quantized), which fits an 8 GB card, against 29.1 GB at BF16. 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 HarmBench-Llama-2-13b-cls lower the GPU bill?
Yes. At BF16 the cheapest live fit is one RTX 4080 Super at $0.338/hr. At INT4 (quantized) it drops to one RTX 3060 at $0.110/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More cais models
- bert-base-uncased (110M, F32)
- Qwen3-0.6B (752M, BF16)
- gpt2 (137M, F32)
- Qwen3-8B (8.2B, BF16)
- Qwen3.6-35B-A3B-FP8 (36.0B, F8_E4M3)
- Qwen3.5-9B (9.7B, BF16)
Related reading: H100 pricing and specs, The best GPUs for AI, ranked, and Best GPU for LLM inference.
