Mac Studio, M4 Max, 128GB, refurbished vs Ascent GX10, GB10 Grace Blackwell, 128GB
Both hold Llama-4-Scout-17B-16E at Q8_0. Mac Studio, M4 Max, 128GB, refurbished decodes an est. 15.1 tok/s against 7.6, and costs $409.01 more — $54.12 per extra token per second. Worth it if you read the output as it arrives; not if you queue jobs.
For Llama-4-Scout-17B-16E at Q8_0Mac Studio, M4 Max, refurb 128GBAscent GX10, GB10 Grace Blackwell 128GB
- Fit
- Tight
- Tight
- Headroom
- 1GB
- 2GB
- Est. speed
- 15.1 tok/s
- 7.6 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 3d
- $3,999.99 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-120bWon't fitWon't fit
- Mistral-Large-2411Won't fitWon't fit
- Llama-4-Scout-17B-16ETightTight
- 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 Q8_0. The rows where the two boxes agree are dimmed, because they are not what you are choosing between.