Cheapest box to run DeepSeek-V3 at Q4_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 Q4_K_M needs 407GB.
Cheapest Config that fits: Mac Studio, M5 Ultra, 512GB. Fits, 97GB headroom. Est. 26.9 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−394GB headroom
- Mac mini, M6, 24GB$1,299Won't fit−386GB headroom
- Mac mini, M6, 32GB$1,499Won't fit−378GB headroom
- Mac mini, M5 Pro, 24GB$1,699Won't fit−386GB headroom
- Mac mini, M5 Pro, 48GB$2,499Won't fit−363GB headroom
- Mac Studio, M5 Max, 36GB$2,499Won't fit−374GB headroom
- Mac mini, M5 Pro, 64GB$2,899Won't fit−348GB headroom
- Mac Studio, M5 Max, 48GB$3,099Won't fit−363GB headroom
- Mac Studio, M5 Max, 64GB$3,499Won't fit−348GB headroom
- Won't fit−287GB headroom
- Won't fit−287GB headroom
- Won't fit−319GB headroom
- GeForce RTX 5090, 32GB$5,699.99+hostWon't fit−376GB headroom
- Won't fit−159GB headroom
- Fits97GB headroomest. 26.9 tok/s
| Config | Memory | Price | $/GB | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | $69 | Won't fit | −394GB | — |
| Mac mini, M6 | 24GB | $1,299 | $54 | Won't fit | −386GB | — |
| Mac mini, M6 | 32GB | $1,499 | $47 | Won't fit | −378GB | — |
| Mac mini, M5 Pro | 24GB | $1,699 | $71 | Won't fit | −386GB | — |
| Mac mini, M5 Pro | 48GB | $2,499 | $52 | Won't fit | −363GB | — |
| Mac Studio, M5 Max | 36GB | $2,499 | $69 | Won't fit | −374GB | — |
| Mac mini, M5 Pro | 64GB | $2,899 | $45 | Won't fit | −348GB | — |
| Mac Studio, M5 Max | 48GB | $3,099 | $65 | Won't fit | −363GB | — |
| Mac Studio, M5 Max | 64GB | $3,499 | $55 | Won't fit | −348GB | — |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | $37 | Won't fit | −287GB | — |
| Mac Studio, M5 Max | 128GB | $5,099 | $40 | Won't fit | −287GB | — |
| Mac Studio, M5 Ultra | 96GB | $5,499 | $57 | Won't fit | −319GB | — |
| GeForce RTX 5090 | 32GB | $5,699.99+host | $178 | Won't fit | −376GB | — |
| Mac Studio, M5 Ultra | 256GB | $9,499 | $37 | Won't fit | −159GB | — |
| Mac Studio, M5 Ultra | 512GB | — | — | Fits | 97GB | 26.9 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 × 0.604 B/param (4.83 bits) + 0.070 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.5 ÷ (37B active × 0.604 B/param) = 22.3 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.