Mac Studio, M5 Max, 36GB vs Mac Studio, M5 Max, 128GB
Both hold Gemma-3-27B at Q8_0. Mac Studio, M5 Max, 128GB decodes an est. 13.9 tok/s against 10.4, and costs $2,600 more — $745.13 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
- 88GB
- Est. speed
- 10.4 tok/s
- 13.9 tok/s
- Cheapest today
- $2,499 at Best Buy
- $5,099 at Apple
- Per GB of memory
- $69
- $40
- Memory
- 36GB unified memory
- 128GB unified memory
- Usable for a model
- 33GB
- 120GB
- Memory bandwidth
- 460GB/s
- 614GB/s
- Storage
- 512GB
- 512GB
- Lowest recorded
- $2,499 in 47d
- $5,099 in 47d
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-3.3-70BWon't fitFits
- gpt-oss-120bWon't fitWon't fit
- Mistral-Large-2411Won't fitWon't fit
- Llama-4-Scout-17B-16EWon't fitTight
- Qwen3-32BWon't fitFits
- Gemma-3-27BTightFits
- gpt-oss-20bFitsFits
- Llama-4-Maverick-17B-128EWon't fitWon't fit
- Llama-4-BehemothWon't fitWon't fit
- Qwen3-Coder-480B-A35B-InstructWon't fitWon't fit
- Kimi-K2-InstructWon't fitWon't fit
- GLM-4.6Won't fitWon't fit
- DeepSeek-R1Won't fitWon't fit
- MiniMax-M2Won't fitWon't fit
- Qwen3-30B-A3BWon't fitFits
- Qwen3-4BFitsFits
- Devstral-Small-2507FitsFits
- Phi-4FitsFits
- Gemma-3n-E4BFitsFits
- Qwen3-VL-8B-InstructFitsFits
- Qwen3.5-35B-A3BWon't fitFits
- Qwen3.6-27BTightFits
- Qwen3-Coder-NextWon't fitFits
- DeepSeek-V4-FlashWon't fitWon't fit
- DeepSeek-V4-ProWon't fitWon't fit
- Gemma-4-26B-A4BFitsFits
- Gemma-4-31BWon't fitFits
- Gemma-4-12BFitsFits
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.