🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the NVIDIA Jetson T3000 run TinyLlama-1.1B (3T token checkpoint)?
Yes — here's how fast and up to what context, with real measured numbers.
TinyLlama-1.1B (3T token checkpoint) on the NVIDIA Jetson T3000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 383k | 90.6-108 t/s | ~3.3-4 (slow) |
| Q8 | yes | 400k | 181.2-215.9 t/s | ~6.6-7.9 (slow) |
| Q4 | yes | 407k | 323.5-385.6 t/s | ~11.9-14.1 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
→ All models on the NVIDIA Jetson T3000
→ TinyLlama-1.1B (3T token checkpoint) specs
→ Other hardware
FAQ
Can the NVIDIA Jetson T3000 run TinyLlama-1.1B (3T token checkpoint)?▶
Yes. At Q4 it generates ~323.5-385.6 tok/s and fits up to 407k context; beyond that it spills to SSD swap and slows to ~11.9-14.1 tok/s.
How much context fits?▶
At Q4, up to about 407k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.