StableLM models
3 StableLM models from Stability AI on Hugging Face, from 1.6B to 2.8B parameters, published by Stability AI in F16 and BF16, with a 4K-token context. The smallest official model, stablelm-2-zephyr-1_6b, needs about 3.7 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.
Pick a size
One row per official StableLM 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 |
|---|---|---|---|---|---|---|---|
| stablelm-2-zephyr-1_6b | 1.6B | 3.7 GB | 1.8 GB | 0.9 GB | RTX 3070 | $0.088/hr | 6.0 GB |
| stablelm-3b-4e1t | 2.8B | 6.2 GB | 3.1 GB | 1.6 GB | RTX 3070 | $0.088/hr | 10.0 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 (3)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| stablelm-2-zephyr-1_6b | 1.6B | F16 | 3.7 GB | RTX 3070 | $0.088/hr |
| stablelm-3b-4e1t | 2.8B | BF16 | 6.2 GB | RTX 3070 | $0.088/hr |
| stablelm-zephyr-3b | 2.8B | BF16 | 6.2 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.
More from Stability AI
- Stable Diffusion XL (34 models)
- Stable Diffusion 1 (3 models)
- Stable Diffusion 2 (5 models)
- Stable Diffusion 3 (3 models)
- Stable Video Diffusion (2 models)
- stabilityai (4 models)