Cheapest box to run Llama-3.3-70B at BF16
Meta’s Llama-3.3-70B is 70B parameters, dense. 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-3.3-70B at BF16 needs 144GB.
Cheapest Config that fits: Mac Studio, M3 Ultra, 256GB, refurbished. Fits, 104GB headroom. Est. 3.8 tok/s.
Best offer today: $7,729 at Apple Certified Refurbished — in stock, checked 19 minutes 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 19 minutes ago$7,729
- Mac mini, M6, 16GB$1,099Won't fit−131GB headroom
- Mac mini, M6, 24GB$1,299Won't fit−123GB headroom
- Mac mini, M6, 32GB$1,499Won't fit−115GB headroom
- Mac mini, M5 Pro, 24GB$1,699Won't fit−123GB headroom
- Mac mini, M5 Pro, 48GB$2,499Won't fit−100GB headroom
- Mac Studio, M5 Max, 36GB$2,499Won't fit−111GB headroom
- Mac mini, M5 Pro, 64GB$2,899Won't fit−85GB headroom
- GeForce RTX 5090, 32GB$2,999.99+hostWon't fit−113GB headroom
- Won't fit−85GB headroom
- Mac Studio, M5 Max, 48GB$3,099Won't fit−100GB headroom
- Mac Studio, M5 Max, 64GB$3,499Won't fit−85GB headroom
- Won't fit−24GB headroom
- Won't fit−56GB headroom
- Won't fit−24GB headroom
- Won't fit−24GB headroom
- Won't fit−24GB headroom
- Won't fit−56GB headroom
- Fits104GB headroomest. 3.8 tok/s
- Fits104GB headroomest. 5.6 tok/s
- Fits360GB headroomest. 5.6 tok/s
| Config | Memory | Price | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | Won't fit | −131GB | — |
| Mac mini, M6 | 24GB | $1,299 | Won't fit | −123GB | — |
| Mac mini, M6 | 32GB | $1,499 | Won't fit | −115GB | — |
| Mac mini, M5 Pro | 24GB | $1,699 | Won't fit | −123GB | — |
| Mac mini, M5 Pro | 48GB | $2,499 | Won't fit | −100GB | — |
| Mac Studio, M5 Max | 36GB | $2,499 | Won't fit | −111GB | — |
| Mac mini, M5 Pro | 64GB | $2,899 | Won't fit | −85GB | — |
| GeForce RTX 5090 | 32GB | $2,999.99+host | Won't fit | −113GB | — |
| Mac Studio, M4 Max, refurb | 64GB | $3,049 | Won't fit | −85GB | — |
| Mac Studio, M5 Max | 48GB | $3,099 | Won't fit | −100GB | — |
| Mac Studio, M5 Max | 64GB | $3,499 | Won't fit | −85GB | — |
| Ascent GX10, GB10 Grace Blackwell | 128GB | $3,999.99 | Won't fit | −24GB | — |
| Mac Studio, M3 Ultra, refurb | 96GB | $4,329 | Won't fit | −56GB | — |
| Mac Studio, M4 Max, refurb | 128GB | $4,409 | Won't fit | −24GB | — |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | Won't fit | −24GB | — |
| Mac Studio, M5 Max | 128GB | $5,099 | Won't fit | −24GB | — |
| Mac Studio, M5 Ultra | 96GB | $5,499 | Won't fit | −56GB | — |
| Mac Studio, M3 Ultra, refurb | 256GB | $7,729 | Fits | 104GB | 3.8 tok/s |
| Mac Studio, M5 Ultra | 256GB | $9,499 | Fits | 104GB | 5.6 tok/s |
| Mac Studio, M5 Ultra | 512GB | — | Fits | 360GB | 5.6 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 = 70B × 2.000 B/param (16 bits) + 0.328 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.65 ÷ (70B active × 2.000 B/param) = 140.0 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.