Mac Studio, M5 Max, 128GB vs Mac Studio, M5 Ultra, 256GB
Both hold gpt-oss-120b at Q4_K_M. Mac Studio, M5 Ultra, 256GB decodes an est. 195 tok/s against 99.7, and costs $4,400 more — $46.23.941979522184738 per extra token per second. Worth it if you read the output as it arrives; not if you queue jobs.
- Fit
- Fits
- Fits
- Headroom
- 48GB
- 176GB
- Est. speed
- 99.7 tok/s
- 195 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 fitFits
- DeepSeek-V3Won't fitWon't fit
- Llama-3.3-70BFitsFits
- gpt-oss-120bFitsFits
- Mistral-Large-2411FitsFits
- Llama-4-Scout-17B-16EFitsFits
- Qwen3-32BFitsFits
- Gemma-3-27BFitsFits
- gpt-oss-20bFitsFits
- Llama-4-Maverick-17B-128EWon't fitTight
- Llama-4-BehemothWon't fitWon't fit
Every model we track at Q4_K_M. The rows where the two boxes agree are dimmed, because they are not what you are choosing between.