Mac Studio, M5 Max, 128GB vs Mac Studio, M5 Ultra, 256GB
Both hold Llama-4-Scout-17B-16E at Q8_0. Mac Studio, M5 Ultra, 256GB decodes an est. 33.2 tok/s against 17.0, and costs $4,400 more — $271.24.573378839595534 per extra token per second. Worth it if you read the output as it arrives; not if you queue jobs.
- Fit
- Tight
- Fits
- Headroom
- 1GB
- 129GB
- Est. speed
- 17.0 tok/s
- 33.2 tok/s
- Cheapest today
- $5,099 at Apple
- $9,499 at Apple
- Per GB of memory
- $40
- $37
- Memory
- 128GB unified memory
- 256GB unified memory
- Usable for a model
- 120GB
- 248GB
- Memory bandwidth
- 614GB/s
- 1.2TB/s
- Storage
- 512GB
- 1TB
- Lowest recorded
- $5,099 in 2d
- $9,499 in 2d
Fit, headroom and speed are computed from each vendor’s published bandwidth and the model’s own size at 8K context. Prices are the cheapest listing we could read on each seller’s page. The arithmetic is here.
Where they actually differ
- Qwen3-235B-A22BWon't fitWon't fit
- DeepSeek-V3Won't fitWon't fit
- Llama-3.3-70BFitsFits
- gpt-oss-120bWon't fitFits
- Mistral-Large-2411Won't fitFits
- Llama-4-Scout-17B-16ETightFits
- Qwen3-32BFitsFits
- Gemma-3-27BFitsFits
- gpt-oss-20bFitsFits
- Llama-4-Maverick-17B-128EWon't fitWon't fit
- Llama-4-BehemothWon't fitWon't fit
Every model we track at Q8_0. The rows where the two boxes agree are dimmed, because they are not what you are choosing between.