Mac Studio, M3 Ultra, 256GB, refurbished vs Mac Studio, M5 Ultra, 512GB
Both hold Llama-3.3-70B at Q8_0. Mac Studio, M5 Ultra, 512GB is the faster of the two, at an est. 10.5 tok/s against 7.2. We do not have a price for both, so we do not name a winner.
- Fit
- Fits
- Fits
- Headroom
- 170GB
- 426GB
- Est. speed
- 7.2 tok/s
- 10.5 tok/s
- Cheapest today
- $7,729 at Apple Certified Refurbished
- no price yet
- Per GB of memory
- $30
- —
- Memory
- 256GB unified memory
- 512GB unified memory
- Usable for a model
- 248GB
- 504GB
- Memory bandwidth
- 819GB/s
- 1.2TB/s
- Storage
- 1TB
- 1TB
- Lowest recorded
- $7,729 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-120bFitsFits
- Mistral-Large-2411FitsFits
- Llama-4-Scout-17B-16EFitsFits
- 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 fitWon't fit
- Kimi-K2-InstructWon't fitWon't fit
- GLM-4.6Won't fitFits
- DeepSeek-R1Won't fitWon't fit
- MiniMax-M2TightFits
- Qwen3-30B-A3BFitsFits
- Qwen3-4BFitsFits
- Devstral-Small-2507FitsFits
- Phi-4FitsFits
- Gemma-3n-E4BFitsFits
- Qwen3-VL-8B-InstructFitsFits
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.