Cheapest box to run Qwen3.6-27B at BF16
Alibaba’s Qwen3.6-27B is 27B 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.
Qwen3.6-27B at BF16 needs 56GB.
Cheapest Config that fits: Ascent GX10, GB10 Grace Blackwell, 128GB. Fits, 65GB headroom. Est. 3.3 tok/s.
Best offer today: $3,999.99 at Best Buy — in stock, checked 33 days ago.
Price history: 34 days recorded.
Same hybrid family: 16 of 64 layers are full attention; the rest cache nothing per token.
Offers — Ascent GX10, GB10 Grace Blackwell, 128GB, 1TB
- Best BuyRead on 28 Aug 2026 and not re-read since: Best Buy blocks our automated checks, so this number is old and we say so rather than imply it is current. It was $1,999 under ASUS's own store once ASUS raised its price in September.in stockchecked 33 days ago$3,999.99
- ASUSlist pricein stockchecked 2 hours ago$5,999
- Mac mini, M6, 16GB$1,099Won't fit−43GB headroom
- Mac mini, M6, 24GB$1,299Won't fit−35GB headroom
- Mac mini, M6, 32GB$1,499Won't fit−27GB headroom
- Mac mini, M5 Pro, 24GB$1,699Won't fit−35GB headroom
- Mac mini, M5 Pro, 48GB$2,499Won't fit−12GB headroom
- Mac Studio, M5 Max, 36GB$2,499Won't fit−23GB headroom
- Mac mini, M5 Pro, 64GB$2,899Tight3GB headroomest. 3.7 tok/s
- GeForce RTX 5090, 32GB$2,999.99+hostWon't fit−25GB headroom
- Tight3GB headroomest. 6.6 tok/s
- Mac Studio, M5 Max, 48GB$3,099Won't fit−12GB headroom
- Mac Studio, M5 Max, 64GB$3,499Tight3GB headroomest. 7.4 tok/s
- Fits65GB headroomest. 3.3 tok/s
- Fits33GB headroomest. 9.9 tok/s
- Fits64GB headroomest. 6.6 tok/s
- Fits65GB headroomest. 3.3 tok/s
- Fits64GB headroomest. 7.4 tok/s
- Fits33GB headroomest. 14.4 tok/s
- Fits192GB headroomest. 9.9 tok/s
- Fits192GB headroomest. 14.4 tok/s
- Fits448GB headroomest. 14.4 tok/s
| Config | Memory | Price | $/GB | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | $69 | Won't fit | −43GB | — |
| Mac mini, M6 | 24GB | $1,299 | $54 | Won't fit | −35GB | — |
| Mac mini, M6 | 32GB | $1,499 | $47 | Won't fit | −27GB | — |
| Mac mini, M5 Pro | 24GB | $1,699 | $71 | Won't fit | −35GB | — |
| Mac mini, M5 Pro | 48GB | $2,499 | $52 | Won't fit | −12GB | — |
| Mac Studio, M5 Max | 36GB | $2,499 | $69 | Won't fit | −23GB | — |
| Mac mini, M5 Pro | 64GB | $2,899 | $45 | Tight | 3GB | 3.7 tok/s |
| GeForce RTX 5090 | 32GB | $2,999.99+host | $94 | Won't fit | −25GB | — |
| Mac Studio, M4 Max, refurb | 64GB | $3,049 | $48 | Tight | 3GB | 6.6 tok/s |
| Mac Studio, M5 Max | 48GB | $3,099 | $65 | Won't fit | −12GB | — |
| Mac Studio, M5 Max | 64GB | $3,499 | $55 | Tight | 3GB | 7.4 tok/s |
| Ascent GX10, GB10 Grace Blackwell | 128GB | $3,999.99 | $31 | Fits | 65GB | 3.3 tok/s |
| Mac Studio, M3 Ultra, refurb | 96GB | $4,329 | $45 | Fits | 33GB | 9.9 tok/s |
| Mac Studio, M4 Max, refurb | 128GB | $4,409 | $34 | Fits | 64GB | 6.6 tok/s |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | $37 | Fits | 65GB | 3.3 tok/s |
| Mac Studio, M5 Max | 128GB | $5,099 | $40 | Fits | 64GB | 7.4 tok/s |
| Mac Studio, M5 Ultra | 96GB | $5,499 | $57 | Fits | 33GB | 14.4 tok/s |
| Mac Studio, M3 Ultra, refurb | 256GB | $7,729 | $30 | Fits | 192GB | 9.9 tok/s |
| Mac Studio, M5 Ultra | 256GB | $9,499 | $37 | Fits | 192GB | 14.4 tok/s |
| Mac Studio, M5 Ultra | 512GB | — | — | Fits | 448GB | 14.4 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 = 27B × 2.000 B/param (16 bits) + 0.067 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.65 ÷ (27B active × 2.000 B/param) = 54.0 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 Ascent GX10 GB10 Grace Blackwell 128GB runs
- Qwen3-235B-A22BQ3_K_M, est. 12.7 tok/s
- MiniMax-M2Q3_K_M, est. 27.9 tok/s
- Mistral-Large-2411Q6_K, est. 1.8 tok/s
- gpt-oss-120bQ6_K, est. 32.6 tok/s
- Llama-4-Scout-17B-16EQ8_0, est. 7.6 tok/s
- Qwen3-Coder-NextQ8_0, est. 42.8 tok/s
Best quant that still fits at 8K context, largest model first. Full list on the Config page.
Bandwidth 273GB/s, usable memory 120GB of 128GB.