Can SmolLM2 360M run on the RTX 3080 10GB?
Yes. At 8K context the best fit is F16, using about 1.5 GB of the 9.5 GB usable on the RTX 3080 10GB. Estimated speed ceiling: ~1047 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | Max tok/s (est., 8K) |
|---|---|---|---|
| 2-bit (Q2_K) • | 0.9 GB Fits | 1.0 GB Fits | 3475 |
| 3-bit (Q3_K_M) • | 0.9 GB Fits | 1.0 GB Fits | 3238 |
| 4-bit (Q4_K_M) • | 0.9 GB Fits | 1.1 GB Fits | 2809 |
| 5-bit (Q5_K_M) • | 0.9 GB Fits | 1.1 GB Fits | 2621 |
| 6-bit (Q6_K) • | 1.0 GB Fits | 1.1 GB Fits | 2069 |
| 8-bit (Q8_0) • | 1.0 GB Fits | 1.2 GB Fits | 1967 |
| 16-bit (F16/BF16) • | 1.3 GB Fits | 1.5 GB Fits | 1047 |
• real GGUF file size from mradermacher/SmolLM2-360M-GGUF. Speed is a bandwidth ceiling (760 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs SmolLM2 360M: Arc B580 (12 GB, launch MSRP $249) at F16, fully in VRAM at 8K context.
- Largest popular model that fits the RTX 3080 10GB: Qwen3.5 9B (9.7B) at Q6_K, about 8.1 GB at 8K context.
"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.
More
SmolLM2 360M on every GPU and Mac · Every model that runs on the RTX 3080 10GB · Other models that fit 12 GB VRAM · Try other settings in the calculator
Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs
Data: Hugging Face Hub (HuggingFaceTB/SmolLM2-360M), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.