What GPU do I need to run unsloth/Llama-3.2-3B-Instruct?
3.2B parameters, published in BF16. View on Hugging Face
Llama-3.2-3B-Instruct is published by unsloth on Hugging Face, with 182,043 downloads and 99 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.
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 Llama-3.2-3B-Instruct at its published (BF16) precision: 1× RTX 3070 on simplepod, at $0.050/hr per GPU ($0.050/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 unsloth models
- Qwen3.6-27B-NVFP4 (21.2B, F8_E4M3)
- Llama-3.2-1B-Instruct (1.2B, BF16)
- Meta-Llama-3.1-8B-Instruct (8.0B, BF16)
- Qwen3-Embedding-4B (4.0B, BF16)
- GLM-4.7-Flash (31.2B, BF16)
- Qwen2.5-14B-Instruct (14.8B, BF16)
