Can LongCat 2.5 run on the Ryzen AI Max+ 395 128GB?
No. Even at 2-bit with 8K context, LongCat 2.5 needs about 623 GB, more than the 109 GB usable on the Ryzen AI Max+ 395 128GB.
On this machine the GPU and CPU share one memory pool, so CPU offload does not add room. A smaller quant, a shorter context or more memory are the options.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 622 GB No | 623 GB No | 624 GB No | 629 GB No | — |
| 3-bit (Q3_K_M) | 811 GB No | 811 GB No | 812 GB No | 817 GB No | — |
| 4-bit (Q4_K_M) | 1014 GB No | 1014 GB No | 1016 GB No | 1020 GB No | — |
| 5-bit (Q5_K_M) | 1182 GB No | 1182 GB No | 1183 GB No | 1188 GB No | — |
| 6-bit (Q6_K) | 1360 GB No | 1360 GB No | 1362 GB No | 1366 GB No | — |
| 8-bit (Q8_0) | 1762 GB No | 1762 GB No | 1763 GB No | 1768 GB No | — |
| 16-bit (F16/BF16) | 3316 GB No | 3316 GB No | 3317 GB No | 3322 GB No | — |
• real GGUF file size. Speed is a bandwidth ceiling (256 GB/s), not a benchmark. Methodology.
What fits instead
- Nothing we list runs LongCat 2.5 fully in memory at 8K context. It needs a multi-GPU server.
- Largest popular model that fits the Ryzen AI Max+ 395 128GB: gpt-oss 120B (117B, MoE) at F16, about 61.9 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
LongCat 2.5 on every GPU and Mac · Every model that runs on the Ryzen AI Max+ 395 128GB · Other models that fit 64 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 (meituan-longcat/LongCat-2.5), AMD specs. Model data last checked 2026-11-18; refreshed hourly.