Can I run Spark-X2.6-1.7B on an RTX 5070?
Yes
Its published weights (3.42 GB) fit in the 10.8 GB an RTX 5070 can use, with room for ≈ 502K tokens of context.
hf download XHToken/Spark-X2.6-1.7BFiles and context on RTX 5070
Each file of Spark-X2.6-1.7B (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.
| File | Size | On RTX 5070 | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| As published | 3.42 GB | Fits | 502K | 1005K |
| Spark-X2.6-1.7B | 3.42 GB | Fits | 501K | 1004K |
| Q8_0 | 1.82 GB | Fits | 610K | 1M |
| Q4_K_M | 1.77 GB | Fits | 614K | 1M |