Mac Studio, M4 Max, 128GB, refurbished vs Ascent GX10, GB10 Grace Blackwell, 128GB
Both hold gpt-oss-120b at Q3_K_M. Mac Studio, M4 Max, 128GB, refurbished decodes an est. 110 tok/s against 54.8, and costs $409.01 more — $7.47 per extra token per second. Worth it if you read the output as it arrives; not if you queue jobs.
- Fit
- Fits
- Fits
- Headroom
- 61GB
- 61GB
- Est. speed
- 110 tok/s
- 54.8 tok/s
- Cheapest today
- $4,409 at Apple Certified Refurbished
- $3,999.99 at Best Buy
- Per GB of memory
- $34
- $31
- Memory
- 128GB unified memory
- 128GB unified LPDDR5X memory
- Usable for a model
- 120GB
- 120GB
- Memory bandwidth
- 546GB/s
- 273GB/s
- Storage
- 1TB
- 1TB
- Lowest recorded
- $4,409 in 2d
- $3,999.99 in 2d
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.