Cheapest box to run Devstral-Small-2507 at Q4_K_M
Mistral’s Devstral-Small-2507 is 24B 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.
Devstral-Small-2507 at Q4_K_M needs 17GB.
Cheapest Config that fits: Mac mini, M6, 32GB. Fits, 12GB headroom. Est. 7.6 tok/s.
Best offer today: $1,499 at Apple — in stock, checked 49 minutes ago.
Collecting price history — 3 of 90 days. No timing verdict yet.
Offers — Mac mini, M6, 32GB, 512GB
- Mac mini, M6, 16GB$1,099Won't fit−4GB headroom
- Mac mini, M6, 24GB$1,299Tight4GB headroomest. 7.6 tok/s
- Mac mini, M6, 32GB$1,499Fits12GB headroomest. 7.6 tok/s
- Mac mini, M5 Pro, 24GB$1,699Tight4GB headroomest. 13.8 tok/s
- Mac mini, M5 Pro, 48GB$2,499Fits27GB headroomest. 13.8 tok/s
- Mac Studio, M5 Max, 36GB$2,499Fits16GB headroomest. 27.5 tok/s
- Mac mini, M5 Pro, 64GB$2,899Fits42GB headroomest. 13.8 tok/s
- GeForce RTX 5090, 32GB$2,999.99+hostFits14GB headroomest. 80.4 tok/s
- Fits42GB headroomest. 24.5 tok/s
- Mac Studio, M5 Max, 48GB$3,099Fits27GB headroomest. 27.5 tok/s
- Mac Studio, M5 Max, 64GB$3,499Fits42GB headroomest. 27.5 tok/s
- Fits103GB headroomest. 12.2 tok/s
- Fits71GB headroomest. 36.7 tok/s
- Fits103GB headroomest. 24.5 tok/s
- Fits103GB headroomest. 12.2 tok/s
- Fits103GB headroomest. 27.5 tok/s
- Fits71GB headroomest. 53.8 tok/s
- Fits231GB headroomest. 36.7 tok/s
- Fits231GB headroomest. 53.8 tok/s
- Fits487GB headroomest. 53.8 tok/s
| Config | Memory | Price | $/GB | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | $69 | Won't fit | −4GB | — |
| Mac mini, M6 | 24GB | $1,299 | $54 | Tight | 4GB | 7.6 tok/s |
| Mac mini, M6 | 32GB | $1,499 | $47 | Fits | 12GB | 7.6 tok/s |
| Mac mini, M5 Pro | 24GB | $1,699 | $71 | Tight | 4GB | 13.8 tok/s |
| Mac mini, M5 Pro | 48GB | $2,499 | $52 | Fits | 27GB | 13.8 tok/s |
| Mac Studio, M5 Max | 36GB | $2,499 | $69 | Fits | 16GB | 27.5 tok/s |
| Mac mini, M5 Pro | 64GB | $2,899 | $45 | Fits | 42GB | 13.8 tok/s |
| GeForce RTX 5090 | 32GB | $2,999.99+host | $94 | Fits | 14GB | 80.4 tok/s |
| Mac Studio, M4 Max, refurb | 64GB | $3,049 | $48 | Fits | 42GB | 24.5 tok/s |
| Mac Studio, M5 Max | 48GB | $3,099 | $65 | Fits | 27GB | 27.5 tok/s |
| Mac Studio, M5 Max | 64GB | $3,499 | $55 | Fits | 42GB | 27.5 tok/s |
| Ascent GX10, GB10 Grace Blackwell | 128GB | $3,999.99 | $31 | Fits | 103GB | 12.2 tok/s |
| Mac Studio, M3 Ultra, refurb | 96GB | $4,329 | $45 | Fits | 71GB | 36.7 tok/s |
| Mac Studio, M4 Max, refurb | 128GB | $4,409 | $34 | Fits | 103GB | 24.5 tok/s |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | $37 | Fits | 103GB | 12.2 tok/s |
| Mac Studio, M5 Max | 128GB | $5,099 | $40 | Fits | 103GB | 27.5 tok/s |
| Mac Studio, M5 Ultra | 96GB | $5,499 | $57 | Fits | 71GB | 53.8 tok/s |
| Mac Studio, M3 Ultra, refurb | 256GB | $7,729 | $30 | Fits | 231GB | 36.7 tok/s |
| Mac Studio, M5 Ultra | 256GB | $9,499 | $37 | Fits | 231GB | 53.8 tok/s |
| Mac Studio, M5 Ultra | 512GB | — | — | Fits | 487GB | 53.8 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 = 24B × 0.604 B/param (4.83 bits) + 0.164 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.65 ÷ (24B active × 0.604 B/param) = 14.5 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 mini M6 32GB runs
- Qwen3-32BQ5_K_M, est. 4.9 tok/s
- Qwen3-30B-A3BQ6_K, est. 31.4 tok/s
- Gemma-3-27BQ6_K, est. 5.0 tok/s
- Devstral-Small-2507Q8_0, est. 4.3 tok/s
- gpt-oss-20bQ8_0, est. 22.2 tok/s
- Phi-4Q8_0, est. 7.4 tok/s
Best quant that still fits at 8K context, largest model first. Full list on the Config page.
Bandwidth 170GB/s, usable memory 29GB of 32GB.