Cheapest box to run Llama-4-Scout-17B-16E at BF16
Meta’s Llama-4-Scout-17B-16E is 109B parameters, 17B of them read per token. The number below is computed from that and each vendor’s published specs, not asserted. Switch the quant or the context and it recomputes in place.
Llama-4-Scout-17B-16E at BF16 needs 221GB.
Cheapest Config that fits: Mac Studio, M3 Ultra, 256GB, refurbished. Fits, 27GB headroom. Est. 12.0 tok/s.
Best offer today: $7,729 at Apple Certified Refurbished — in stock, checked 1 hour ago.
Price history: 47 days recorded.
Offers — Mac Studio, M3 Ultra, 256GB, 1TB, refurbished
- Apple Certified RefurbishedRefurbished by Apple, with Apple's one-year limited warranty and 14-day returns. Apple says refurbished supply is usually very limited and often runs out, so this row can go dead faster than a new one.in stockchecked 1 hour ago$7,729
- Mac mini, M6, 16GB$1,099Won't fit−208GB headroom
- Mac mini, M6, 24GB$1,299Won't fit−200GB headroom
- Mac mini, M6, 32GB$1,499Won't fit−192GB headroom
- Mac mini, M5 Pro, 24GB$1,699Won't fit−200GB headroom
- Mac mini, M5 Pro, 48GB$2,499Won't fit−177GB headroom
- Mac Studio, M5 Max, 36GB$2,499Won't fit−188GB headroom
- Mac mini, M5 Pro, 64GB$2,899Won't fit−162GB headroom
- GeForce RTX 5090, 32GB$2,999.99+hostWon't fit−190GB headroom
- Won't fit−162GB headroom
- Mac Studio, M5 Max, 48GB$3,099Won't fit−177GB headroom
- Mac Studio, M5 Max, 64GB$3,499Won't fit−162GB headroom
- Won't fit−100GB headroom
- Won't fit−132GB headroom
- Won't fit−101GB headroom
- Won't fit−100GB headroom
- Won't fit−101GB headroom
- Won't fit−132GB headroom
- Fits27GB headroomest. 12.0 tok/s
- Fits27GB headroomest. 17.6 tok/s
- Fits283GB headroomest. 17.6 tok/s
| Config | Memory | Price | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | Won't fit | −208GB | — |
| Mac mini, M6 | 24GB | $1,299 | Won't fit | −200GB | — |
| Mac mini, M6 | 32GB | $1,499 | Won't fit | −192GB | — |
| Mac mini, M5 Pro | 24GB | $1,699 | Won't fit | −200GB | — |
| Mac mini, M5 Pro | 48GB | $2,499 | Won't fit | −177GB | — |
| Mac Studio, M5 Max | 36GB | $2,499 | Won't fit | −188GB | — |
| Mac mini, M5 Pro | 64GB | $2,899 | Won't fit | −162GB | — |
| GeForce RTX 5090 | 32GB | $2,999.99+host | Won't fit | −190GB | — |
| Mac Studio, M4 Max, refurb | 64GB | $3,049 | Won't fit | −162GB | — |
| Mac Studio, M5 Max | 48GB | $3,099 | Won't fit | −177GB | — |
| Mac Studio, M5 Max | 64GB | $3,499 | Won't fit | −162GB | — |
| Ascent GX10, GB10 Grace Blackwell | 128GB | $3,999.99 | Won't fit | −100GB | — |
| Mac Studio, M3 Ultra, refurb | 96GB | $4,329 | Won't fit | −132GB | — |
| Mac Studio, M4 Max, refurb | 128GB | $4,409 | Won't fit | −101GB | — |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | Won't fit | −100GB | — |
| Mac Studio, M5 Max | 128GB | $5,099 | Won't fit | −101GB | — |
| Mac Studio, M5 Ultra | 96GB | $5,499 | Won't fit | −132GB | — |
| Mac Studio, M3 Ultra, refurb | 256GB | $7,729 | Fits | 27GB | 12.0 tok/s |
| Mac Studio, M5 Ultra | 256GB | $9,499 | Fits | 27GB | 17.6 tok/s |
| Mac Studio, M5 Ultra | 512GB | — | Fits | 283GB | 17.6 tok/s |
GeForce RTX 5090 is a card, not a computer: every price shown for it is the cheapest listing we found plus $1,000 for the minimum host machine.
memory = 109B × 2.000 B/param (16 bits) + 0.197 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.5 ÷ (17B active × 2.000 B/param) = 34.0 GB read per token
usable = memory − operating system reserve (8% on a Mac, 6% on a DGX Spark, 4% on a card)
Bandwidth is the vendor’s published figure. Every speed is an estimate and says so. Methodology.
What else Mac Studio M3 Ultra 256GB refurb runs
- Qwen3-Coder-480B-A35B-InstructQ3_K_M, est. 23.9 tok/s
- Llama-4-Maverick-17B-128EQ4_K_M, est. 39.9 tok/s
- GLM-4.6Q4_K_M, est. 21.2 tok/s
- DeepSeek-V4-FlashQ6_K, est. 38.4 tok/s
- Qwen3-235B-A22BQ6_K, est. 22.7 tok/s
- MiniMax-M2Q8_0, est. 38.5 tok/s
Best quant that still fits at 8K context, largest model first. Full list on the Config page.
Bandwidth 819GB/s, usable memory 248GB of 256GB.