Mac Studio, M5 Ultra, 96GB vs Mac Studio, M5 Ultra, 512GB
Both hold Gemma-3-27B at Q6_K. Mac Studio, M5 Ultra, 96GB is the faster of the two, at an est. 35.2 tok/s against 35.2. We do not have a price for both, so we do not name a winner.
- Fit
- Fits
- Fits
- Headroom
- 63GB
- 479GB
- Est. speed
- 35.2 tok/s
- 35.2 tok/s
- Cheapest today
- $5,499 at Apple
- no price yet
- Per GB of memory
- $57
- —
- Memory
- 96GB unified memory
- 512GB unified memory
- Usable for a model
- 88GB
- 504GB
- Memory bandwidth
- 1.2TB/s
- 1.2TB/s
- Storage
- 1TB
- 1TB
- Lowest recorded
- $5,499 in 3d
- none yet
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-120bWon't fitFits
- Mistral-Large-2411Won't fitFits
- Llama-4-Scout-17B-16EWon't fitFits
- Qwen3-32BFitsFits
- Gemma-3-27BFitsFits
- gpt-oss-20bFitsFits
- Llama-4-Maverick-17B-128EWon't fitFits
- Llama-4-BehemothWon't fitWon't fit
- Qwen3-Coder-480B-A35B-InstructWon't fitFits
- Kimi-K2-InstructWon't fitWon't fit
- GLM-4.6Won't fitFits
- DeepSeek-R1Won't fitWon't fit
- MiniMax-M2Won't fitFits
- Qwen3-30B-A3BFitsFits
- Qwen3-4BFitsFits
- Devstral-Small-2507FitsFits
- Phi-4FitsFits
- Gemma-3n-E4BFitsFits
- Qwen3-VL-8B-InstructFitsFits
Every model we track at Q6_K. The rows where the two boxes agree are dimmed, because they are not what you are choosing between.