What GPU do I need to run enfuse/smol-tools-4b-32k?
5.2B parameters, published in BF16. View on Hugging Face
Set up smol-tools-4b-32ksmol-tools-4b-32k is published by enfuse on Hugging Face, with 57,181 downloads and 1 like to date. It's a Qwen3_5ForConditionalGeneration 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 | 9.6 GB | 11.6 GB | RTX 4070 Super | 1 | $0.121/hr |
| FP8 (quantized) | 4.8 GB | 5.8 GB | RTX 4070 Super | 1 | $0.121/hr |
| INT4 (quantized) | 2.4 GB | 2.9 GB | RTX 4070 Super | 1 | $0.121/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 smol-tools-4b-32k at its published (BF16) precision: 1× RTX 4070 Super, at $0.121/hr per GPU ($0.121/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
smol-tools-4b-32k: common questions
Does smol-tools-4b-32k fit on a 12 GB GPU?
Yes. At BF16 it needs 11.6 GB of VRAM, so a 12 GB card holds it with 0.4 GB to spare. An 8 GB card is not enough for it at BF16.
What is the least VRAM smol-tools-4b-32k can run in?
2.9 GB, at INT4 (quantized), which fits a 6 GB card, against 11.6 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.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Qwen3.5 models
- Qwen3.5-4B (4.7B, BF16)
- Qwen3.5-4B-Base (4.7B, BF16)
- Qwen3.5-4B (4.7B, BF16)
- Qwen3.5-4B-AWQ (4.7B, BF16)
- Qwen3.8-4B-Distill (4.7B, BF16)
Related reading: H100 pricing and specs, The best GPUs for AI, ranked, and Best GPU for LLM inference.
