Can I run MiMo-V2.6-Distill-Qwen-9B-Ablitrated on an RTX 5070?
Probably, at 4-bit
The published weights are too big, but a 4-bit version (about 5.29 GB) would fit, with room for ≈ 163K tokens of context. The site hasn't analyzed a GGUF of MiMo-V2.6-Distill-Qwen-9B-Ablitrated yet.
Files and context on RTX 5070
Each file of MiMo-V2.6-Distill-Qwen-9B-Ablitrated (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 | 18.8 GB | Doesn't fit | — | — |
| 4-bit (estimate) | 5.29 GB | Fits | 163K | 256K |