🔌
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 T2000 run HGRN 1B (WT 103)?
Yes — here's how fast and up to what context, with real measured numbers.
HGRN 1B (WT 103) on the NVIDIA Jetson T2000
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 166k | 50-59.6 t/s | ~3.7-4.4 (slow) |
| Q8 | yes | 182k | 100-119.2 t/s | ~7.3-8.7 (slow) |
| Q4 | yes | 188k | 178.6-212.8 t/s | ~13-15.5 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
FAQ
Can the NVIDIA Jetson T2000 run HGRN 1B (WT 103)?▶
Yes. At Q4 it generates ~178.6-212.8 tok/s and fits up to 188k context; beyond that it spills to SSD swap and slows to ~13-15.5 tok/s.
How much context fits?▶
At Q4, up to about 188k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.