Cheapest box to run Qwen3-235B-A22B at Q3_K_M
Alibaba’s Qwen3-235B-A22B is 235B parameters, 22B 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.
Qwen3-235B-A22B at Q3_K_M needs 118GB.
Cheapest Config that fits: Mac Studio, M3 Ultra, 256GB, refurbished. Fits, 130GB headroom. Est. 38.1 tok/s.
Best offer today: $7,729 at Apple Certified Refurbished — in stock, checked 48 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 48 minutes ago$7,729
- Mac mini, M6, 16GB$1,099Won't fit−105GB headroom
- Mac mini, M6, 24GB$1,299Won't fit−97GB headroom
- Mac mini, M6, 32GB$1,499Won't fit−89GB headroom
- Mac mini, M5 Pro, 24GB$1,699Won't fit−97GB headroom
- Mac mini, M5 Pro, 48GB$2,499Won't fit−73GB headroom
- Mac Studio, M5 Max, 36GB$2,499Won't fit−85GB headroom
- Mac mini, M5 Pro, 64GB$2,899Won't fit−59GB headroom
- GeForce RTX 5090, 32GB$2,999.99+hostWon't fit−87GB headroom
- Won't fit−59GB headroom
- Mac Studio, M5 Max, 48GB$3,099Won't fit−73GB headroom
- Mac Studio, M5 Max, 64GB$3,499Won't fit−59GB headroom
- Tight3GB headroomest. 12.7 tok/s
- Won't fit−29GB headroom
- Tight2GB headroomest. 25.4 tok/s
- Tight3GB headroomest. 12.7 tok/s
- Tight2GB headroomest. 28.6 tok/s
- Won't fit−29GB headroom
- Fits130GB headroomest. 38.1 tok/s
- Fits130GB headroomest. 55.8 tok/s
- Fits386GB headroomest. 55.8 tok/s
| Config | Memory | Price | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | Won't fit | −105GB | — |
| Mac mini, M6 | 24GB | $1,299 | Won't fit | −97GB | — |
| Mac mini, M6 | 32GB | $1,499 | Won't fit | −89GB | — |
| Mac mini, M5 Pro | 24GB | $1,699 | Won't fit | −97GB | — |
| Mac mini, M5 Pro | 48GB | $2,499 | Won't fit | −73GB | — |
| Mac Studio, M5 Max | 36GB | $2,499 | Won't fit | −85GB | — |
| Mac mini, M5 Pro | 64GB | $2,899 | Won't fit | −59GB | — |
| GeForce RTX 5090 | 32GB | $2,999.99+host | Won't fit | −87GB | — |
| Mac Studio, M4 Max, refurb | 64GB | $3,049 | Won't fit | −59GB | — |
| Mac Studio, M5 Max | 48GB | $3,099 | Won't fit | −73GB | — |
| Mac Studio, M5 Max | 64GB | $3,499 | Won't fit | −59GB | — |
| Ascent GX10, GB10 Grace Blackwell | 128GB | $3,999.99 | Tight | 3GB | 12.7 tok/s |
| Mac Studio, M3 Ultra, refurb | 96GB | $4,329 | Won't fit | −29GB | — |
| Mac Studio, M4 Max, refurb | 128GB | $4,409 | Tight | 2GB | 25.4 tok/s |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | Tight | 3GB | 12.7 tok/s |
| Mac Studio, M5 Max | 128GB | $5,099 | Tight | 2GB | 28.6 tok/s |
| Mac Studio, M5 Ultra | 96GB | $5,499 | Won't fit | −29GB | — |
| Mac Studio, M3 Ultra, refurb | 256GB | $7,729 | Fits | 130GB | 38.1 tok/s |
| Mac Studio, M5 Ultra | 256GB | $9,499 | Fits | 130GB | 55.8 tok/s |
| Mac Studio, M5 Ultra | 512GB | — | Fits | 386GB | 55.8 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 = 235B × 0.489 B/param (3.91 bits) + 0.193 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.5 ÷ (22B active × 0.489 B/param) = 10.8 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.