Can MiniMax M1 40K run on the RTX 4070 Ti?
No. Even at 2-bit with 8K context, MiniMax M1 40K needs about 163 GB, more than the 11.4 GB usable on the RTX 4070 Ti.
Even with llama.cpp CPU offload (-ngl, --n-cpu-moe) and 128 GB of system RAM, this model does not fit at 2-bit, or the card cannot hold a useful share of it. See the offload method.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 161 GB No | 163 GB No | 170 GB No | 200 GB No | — |
| 3-bit (Q3_K_M) | 210 GB No | 211 GB No | 218 GB No | 248 GB No | — |
| 4-bit (Q4_K_M) | 262 GB No | 263 GB No | 270 GB No | 300 GB No | — |
| 5-bit (Q5_K_M) | 305 GB No | 306 GB No | 313 GB No | 343 GB No | — |
| 6-bit (Q6_K) | 350 GB No | 352 GB No | 359 GB No | 389 GB No | — |
| 8-bit (Q8_0) | 453 GB No | 455 GB No | 462 GB No | 492 GB No | — |
| 16-bit (F16/BF16) | 852 GB No | 853 GB No | 860 GB No | 890 GB No | — |
• real GGUF file size. Speed is a bandwidth ceiling (504 GB/s), not a benchmark. Methodology.
Hardware that does fit it
Mac M3 Ultra 256GBMac M3 Ultra 512GB
What fits instead
- No listed GPU with a list price runs MiniMax M1 40K fully in memory. The smallest listed hardware that does is the Mac M3 Ultra 256GB (256 GB).
- Largest popular model that fits the RTX 4070 Ti: KORMo Web 11B (11B) at Q5_K_M, about 9.3 GB at 8K context.
"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.
More
MiniMax M1 40K on every GPU and Mac · Every model that runs on the RTX 4070 Ti · Other models that fit 12 GB VRAM · Try other settings in the calculator
Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs
Data: Hugging Face Hub (MiniMaxAI/MiniMax-M1-40k), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.