Compare calculated local requirements, provider-published rented-GPU rates, and dated API rates or clearly labeled size estimates for TinyLlama 1.1B Chat v1.0 and phi 2. Spanvero adds $0 markup.
| TinyLlama 1.1B Chat v1.0 | phi 2 | |
|---|---|---|
| Parameters | 1.1B | 2.8B |
| Context window | 2K | 2K |
| License | Commercial OK | Commercial OK |
| VRAM to run | ✓ ~2.0 GB (Q4_K_M) | ~4.0 GB (Q4_K_M) |
| Rent a GPU | $0.06/hr | $0.06/hr |
| Your API key | ✓ $0.11/1M (est.) | $0.12/1M (est.) |
VRAM is calculated from catalog specs, quantization, and context. Non-estimated API rates are provider-sourced snapshots dated 2026-08-24; retired upstream rates are last-known and size-derived values are labeled "est." We don't rank model quality or quote benchmarks here.
Full cost breakdown: TinyLlama 1.1B Chat v1.0 →
Full cost breakdown: phi 2 →
Open the free LLM cost calculator → to model your workload, hardware, monthly cost, and reliability assumptions.
Spanvero · All comparisons · Prices as of 2026-08-24. $0 markup, your own accounts, we never resell compute. © 2026 Cynosure LLC.
A short email of real AI price moves, straight from the daily log — no hype. We're collecting the list now; the first issue goes out when it opens. Unsubscribe with one click.