Cheapest box to run Qwen3-Coder-Next at BF16
Alibaba’s Qwen3-Coder-Next is 80B parameters, 3B 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.
Qwen3-Coder-Next at BF16 needs 161GB.
Cheapest Config that fits: Mac Studio, M3 Ultra, 256GB, refurbished. Fits, 87GB headroom. Est. 68.3 tok/s.
Best offer today: $7,729 at Apple Certified Refurbished — in stock, checked 2 hours ago.
Price history: 34 days recorded.
The Qwen3-Next hybrid again: 12 of 48 layers are full attention and the linear layers cache nothing per token.
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 2 hours ago$7,729
- Mac mini, M6, 16GB$1,099Won't fit−148GB headroom
- Mac mini, M6, 24GB$1,299Won't fit−140GB headroom
- Mac mini, M6, 32GB$1,499Won't fit−132GB headroom
- Mac mini, M5 Pro, 24GB$1,699Won't fit−140GB headroom
- Mac mini, M5 Pro, 48GB$2,499Won't fit−117GB headroom
- Mac Studio, M5 Max, 36GB$2,499Won't fit−128GB headroom
- Mac mini, M5 Pro, 64GB$2,899Won't fit−103GB headroom
- GeForce RTX 5090, 32GB$2,999.99+hostWon't fit−131GB headroom
- Won't fit−103GB headroom
- Mac Studio, M5 Max, 48GB$3,099Won't fit−117GB headroom
- Mac Studio, M5 Max, 64GB$3,499Won't fit−103GB headroom
- Won't fit−41GB headroom
- Won't fit−73GB headroom
- Won't fit−41GB headroom
- Won't fit−41GB headroom
- Won't fit−41GB headroom
- Won't fit−73GB headroom
- Fits87GB headroomest. 68.3 tok/s
- Fits87GB headroomest. 100 tok/s
- Fits343GB headroomest. 100 tok/s
| Config | Memory | Price | $/GB | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | $69 | Won't fit | −148GB | — |
| Mac mini, M6 | 24GB | $1,299 | $54 | Won't fit | −140GB | — |
| Mac mini, M6 | 32GB | $1,499 | $47 | Won't fit | −132GB | — |
| Mac mini, M5 Pro | 24GB | $1,699 | $71 | Won't fit | −140GB | — |
| Mac mini, M5 Pro | 48GB | $2,499 | $52 | Won't fit | −117GB | — |
| Mac Studio, M5 Max | 36GB | $2,499 | $69 | Won't fit | −128GB | — |
| Mac mini, M5 Pro | 64GB | $2,899 | $45 | Won't fit | −103GB | — |
| GeForce RTX 5090 | 32GB | $2,999.99+host | $94 | Won't fit | −131GB | — |
| Mac Studio, M4 Max, refurb | 64GB | $3,049 | $48 | Won't fit | −103GB | — |
| Mac Studio, M5 Max | 48GB | $3,099 | $65 | Won't fit | −117GB | — |
| Mac Studio, M5 Max | 64GB | $3,499 | $55 | Won't fit | −103GB | — |
| Ascent GX10, GB10 Grace Blackwell | 128GB | $3,999.99 | $31 | Won't fit | −41GB | — |
| Mac Studio, M3 Ultra, refurb | 96GB | $4,329 | $45 | Won't fit | −73GB | — |
| Mac Studio, M4 Max, refurb | 128GB | $4,409 | $34 | Won't fit | −41GB | — |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | $37 | Won't fit | −41GB | — |
| Mac Studio, M5 Max | 128GB | $5,099 | $40 | Won't fit | −41GB | — |
| Mac Studio, M5 Ultra | 96GB | $5,499 | $57 | Won't fit | −73GB | — |
| Mac Studio, M3 Ultra, refurb | 256GB | $7,729 | $30 | Fits | 87GB | 68.3 tok/s |
| Mac Studio, M5 Ultra | 256GB | $9,499 | $37 | Fits | 87GB | 100 tok/s |
| Mac Studio, M5 Ultra | 512GB | — | — | Fits | 343GB | 100 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 = 80B × 2.000 B/param (16 bits) + 0.025 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.5 ÷ (3B active × 2.000 B/param) = 6.0 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.