Cheapest box to run DeepSeek-V3 at Q5_K_M
DeepSeek’s DeepSeek-V3 is 671B parameters, 37B 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.
DeepSeek-V3 at Q5_K_M needs 477GB.
Cheapest Config that fits: Mac Studio, M5 Ultra, 512GB. Tight, only 27GB spare. Est. 22.9 tok/s.
No price yet: Ships late October 2026. Apple has not published a price.
Collecting price history — 1 of 90 days. No timing verdict yet.
Offers — Mac Studio, M5 Ultra, 512GB, 1TB
Ships late October 2026. Apple has not published a price.
- Mac mini, M6, 16GB$1,099Won't fit−464GB headroom
- Mac mini, M6, 24GB$1,299Won't fit−456GB headroom
- Mac mini, M6, 32GB$1,499Won't fit−448GB headroom
- Mac mini, M5 Pro, 24GB$1,699Won't fit−456GB headroom
- Mac mini, M5 Pro, 48GB$2,499Won't fit−433GB headroom
- Mac Studio, M5 Max, 36GB$2,499Won't fit−444GB headroom
- Mac mini, M5 Pro, 64GB$2,899Won't fit−418GB headroom
- Mac Studio, M5 Max, 48GB$3,099Won't fit−433GB headroom
- Mac Studio, M5 Max, 64GB$3,499Won't fit−418GB headroom
- Won't fit−357GB headroom
- Won't fit−357GB headroom
- Won't fit−389GB headroom
- GeForce RTX 5090, 32GB$5,699.99+hostWon't fit−447GB headroom
- Won't fit−229GB headroom
- Tight27GB headroomest. 22.9 tok/s
| Config | Memory | Price | $/GB | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | $69 | Won't fit | −464GB | — |
| Mac mini, M6 | 24GB | $1,299 | $54 | Won't fit | −456GB | — |
| Mac mini, M6 | 32GB | $1,499 | $47 | Won't fit | −448GB | — |
| Mac mini, M5 Pro | 24GB | $1,699 | $71 | Won't fit | −456GB | — |
| Mac mini, M5 Pro | 48GB | $2,499 | $52 | Won't fit | −433GB | — |
| Mac Studio, M5 Max | 36GB | $2,499 | $69 | Won't fit | −444GB | — |
| Mac mini, M5 Pro | 64GB | $2,899 | $45 | Won't fit | −418GB | — |
| Mac Studio, M5 Max | 48GB | $3,099 | $65 | Won't fit | −433GB | — |
| Mac Studio, M5 Max | 64GB | $3,499 | $55 | Won't fit | −418GB | — |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | $37 | Won't fit | −357GB | — |
| Mac Studio, M5 Max | 128GB | $5,099 | $40 | Won't fit | −357GB | — |
| Mac Studio, M5 Ultra | 96GB | $5,499 | $57 | Won't fit | −389GB | — |
| GeForce RTX 5090 | 32GB | $5,699.99+host | $178 | Won't fit | −447GB | — |
| Mac Studio, M5 Ultra | 256GB | $9,499 | $37 | Won't fit | −229GB | — |
| Mac Studio, M5 Ultra | 512GB | — | — | Tight | 27GB | 22.9 tok/s |
GeForce RTX 5090 is a card, not a computer: its price is the US street median plus $1,000 for the minimum host machine. NVIDIA's $1,999 MSRP is not a price anyone pays.
memory = 671B × 0.709 B/param (5.67 bits) + 0.070 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.5 ÷ (37B active × 0.709 B/param) = 26.2 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 M5 Ultra 512GB runs
- DeepSeek-V3Q5_K_M, est. 22.9 tok/s
- Llama-4-Maverick-17B-128EQ8_0, est. 33.2 tok/s
- Qwen3-235B-A22BBF16, est. 13.6 tok/s
- Mistral-Large-2411BF16, est. 3.2 tok/s
- gpt-oss-120bBF16, est. 58.8 tok/s
- Llama-4-Scout-17B-16EBF16, est. 17.6 tok/s
Best quant that still fits at 8K context, largest model first. Full list on the Config page.
Bandwidth 1.2TB/s, usable memory 504GB of 512GB.