Mac Studio, M4 Max, 128GB, refurbished vs DGX Spark, GB10 Grace Blackwell, 128GB
Both hold Qwen3-32B at Q3_K_M, and DGX Spark, GB10 Grace Blackwell, 128GB is not meaningfully faster — an est. 11.3 tok/s against 22.7. Buy Mac Studio, M4 Max, 128GB, refurbished and keep the $290.
- Fit
- Fits
- Fits
- Headroom
- 101GB
- 101GB
- Est. speed
- 22.7 tok/s
- 11.3 tok/s
- Cheapest today
- $4,409 at Apple Certified Refurbished
- $4,699 at NVIDIA
- Per GB of memory
- $34
- $37
- Memory
- 128GB unified memory
- 128GB unified LPDDR5X memory
- Usable for a model
- 120GB
- 120GB
- Memory bandwidth
- 546GB/s
- 273GB/s
- Storage
- 1TB
- 4TB
- Lowest recorded
- $4,409 in 3d
- $4,699 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-A22BTightTight
- 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-M2TightTight
- Qwen3-30B-A3BFitsFits
- Qwen3-4BFitsFits
- Devstral-Small-2507FitsFits
- Phi-4FitsFits
- Gemma-3n-E4BFitsFits
- Qwen3-VL-8B-InstructFitsFits
Every model we track at Q3_K_M. The rows where the two boxes agree are dimmed, because they are not what you are choosing between.