SmolLM2 models
6 SmolLM2 models from Hugging Face on Hugging Face, from 135M to 1.7B parameters, published by Hugging Face in BF16, with a 8K-token context. The smallest official model, SmolLM2-135M, needs about 0.3 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.
Part of the SmolLM series · Previous generation: SmolLM-1 · Next generation: SmolLM3
Pick a size
One row per official SmolLM2 size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| SmolLM2-135M | 135M | 0.3 GB | 0.2 GB | 0.1 GB | RTX 3070 | $0.088/hr | 0.70 GB |
| SmolLM2-360M | 362M | 0.8 GB | 0.4 GB | 0.2 GB | RTX 3070 | $0.088/hr | 1.3 GB |
| SmolLM2-1.7B | 1.7B | 3.8 GB | 1.9 GB | 1.0 GB | RTX 3070 | $0.088/hr | 6.0 GB |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (6)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| SmolLM2-135M | 135M | BF16 | 0.3 GB | RTX 3070 | $0.088/hr |
| SmolLM2-135M-Instruct | 135M | BF16 | 0.3 GB | RTX 3070 | $0.088/hr |
| SmolLM2-360M | 362M | BF16 | 0.8 GB | RTX 3070 | $0.088/hr |
| SmolLM2-360M-Instruct | 362M | BF16 | 0.8 GB | RTX 3070 | $0.088/hr |
| SmolLM2-1.7B | 1.7B | BF16 | 3.8 GB | RTX 3070 | $0.088/hr |
| SmolLM2-1.7B-Instruct | 1.7B | BF16 | 3.8 GB | RTX 3070 | $0.088/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.