Mac Studio, M3 Ultra, 96GB, refurbished vs Mac Studio, M4 Max, 128GB, refurbished
Both hold Llama-4-Scout-17B-16E at Q4_K_M, and Mac Studio, M4 Max, 128GB, refurbished is not meaningfully faster — an est. 26.6 tok/s against 39.9. Buy Mac Studio, M3 Ultra, 96GB, refurbished and keep the $80.
For Llama-4-Scout-17B-16E at Q4_K_MMac Studio, M3 Ultra, refurb 96GBMac Studio, M4 Max, refurb 128GB
- Fit
- Fits
- Fits
- Headroom
- 20GB
- 51GB
- Est. speed
- 39.9 tok/s
- 26.6 tok/s
- Cheapest today
- $4,329 at Apple Certified Refurbished
- $4,409 at Apple Certified Refurbished
- Per GB of memory
- $45
- $34
- Memory
- 96GB unified memory
- 128GB unified memory
- Usable for a model
- 88GB
- 120GB
- Memory bandwidth
- 819GB/s
- 546GB/s
- Storage
- 1TB
- 1TB
- Lowest recorded
- $4,329 in 3d
- $4,409 in 3d
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-3.3-70BFitsFits
- 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 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
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.