Mac Studio, M5 Max, 36GB vs Mac Studio, M5 Max, 64GB
Both hold Gemma-3-27B at Q4_K_M. Mac Studio, M5 Max, 64GB decodes an est. 24.5 tok/s against 18.3, and costs $1,000 more — $162.85 per extra token per second. Worth it if you read the output as it arrives; not if you queue jobs.
- Fit
- Fits
- Fits
- Headroom
- 13GB
- 39GB
- Est. speed
- 18.3 tok/s
- 24.5 tok/s
- Cheapest today
- $2,499 at Apple
- $3,499 at Apple
- Per GB of memory
- $69
- $55
- Memory
- 36GB unified memory
- 64GB unified memory
- Usable for a model
- 33GB
- 59GB
- Memory bandwidth
- 460GB/s
- 614GB/s
- Storage
- 512GB
- 512GB
- Lowest recorded
- $2,499 in 47d
- $3,499 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 fitWon't fit
- Qwen3-32BFitsFits
- Gemma-3-27BFitsFits
- 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-A3BFitsFits
- Qwen3-4BFitsFits
- Devstral-Small-2507FitsFits
- Phi-4FitsFits
- Gemma-3n-E4BFitsFits
- Qwen3-VL-8B-InstructFitsFits
- Qwen3.5-35B-A3BFitsFits
- Qwen3.6-27BFitsFits
- Qwen3-Coder-NextWon't fitFits
- DeepSeek-V4-FlashWon't fitWon't fit
- DeepSeek-V4-ProWon't fitWon't fit
- Gemma-4-26B-A4BFitsFits
- Gemma-4-31BFitsFits
- Gemma-4-12BFitsFits
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.