Can I run apex-flash-1 on an NVIDIA B300?
Probably, at 4-bit
The published weights are too big, but a 4-bit version (about 181 GB) would fit, with room for ≈ 1M tokens of context. The site hasn't analyzed a GGUF of apex-flash-1 yet.
Files and context on NVIDIA B300
Each file of apex-flash-1 (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 NVIDIA B300 | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| As published | 643 GB | Doesn't fit | — | — |
| 4-bit (estimate) | 181 GB | Fits | 1M | 1M |