Cheapest box to run Llama-4-Maverick-17B-128E at Q4_K_M
Meta’s Llama-4-Maverick-17B-128E is 400B parameters, 17B 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.
Llama-4-Maverick-17B-128E at Q4_K_M needs 244GB.
Cheapest Config that fits: Mac Studio, M5 Ultra, 512GB. Fits, 260GB headroom. Est. 58.5 tok/s.
No price yet: Ships late October 2026. Apple has not published a price.
Collecting price history — 2 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−231GB headroom
- Mac mini, M6, 24GB$1,299Won't fit−223GB headroom
- Mac mini, M6, 32GB$1,499Won't fit−215GB headroom
- Mac mini, M5 Pro, 24GB$1,699Won't fit−223GB headroom
- Mac mini, M5 Pro, 48GB$2,499Won't fit−200GB headroom
- Mac Studio, M5 Max, 36GB$2,499Won't fit−211GB headroom
- Mac mini, M5 Pro, 64GB$2,899Won't fit−185GB headroom
- GeForce RTX 5090, 32GB$2,999.99+hostWon't fit−214GB headroom
- Mac Studio, M5 Max, 48GB$3,099Won't fit−200GB headroom
- Mac Studio, M5 Max, 64GB$3,499Won't fit−185GB headroom
- Won't fit−124GB headroom
- Won't fit−124GB headroom
- Won't fit−124GB headroom
- Won't fit−156GB headroom
- Tight4GB headroomest. 58.5 tok/s
- Fits260GB headroomest. 58.5 tok/s
| Config | Memory | Price | $/GB | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | $69 | Won't fit | −231GB | — |
| Mac mini, M6 | 24GB | $1,299 | $54 | Won't fit | −223GB | — |
| Mac mini, M6 | 32GB | $1,499 | $47 | Won't fit | −215GB | — |
| Mac mini, M5 Pro | 24GB | $1,699 | $71 | Won't fit | −223GB | — |
| Mac mini, M5 Pro | 48GB | $2,499 | $52 | Won't fit | −200GB | — |
| Mac Studio, M5 Max | 36GB | $2,499 | $69 | Won't fit | −211GB | — |
| Mac mini, M5 Pro | 64GB | $2,899 | $45 | Won't fit | −185GB | — |
| GeForce RTX 5090 | 32GB | $2,999.99+host | $94 | Won't fit | −214GB | — |
| Mac Studio, M5 Max | 48GB | $3,099 | $65 | Won't fit | −200GB | — |
| Mac Studio, M5 Max | 64GB | $3,499 | $55 | Won't fit | −185GB | — |
| Ascent GX10, GB10 Grace Blackwell | 128GB | $3,999.99 | $31 | Won't fit | −124GB | — |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | $37 | Won't fit | −124GB | — |
| Mac Studio, M5 Max | 128GB | $5,099 | $40 | Won't fit | −124GB | — |
| Mac Studio, M5 Ultra | 96GB | $5,499 | $57 | Won't fit | −156GB | — |
| Mac Studio, M5 Ultra | 256GB | $9,499 | $37 | Tight | 4GB | 58.5 tok/s |
| Mac Studio, M5 Ultra | 512GB | — | — | Fits | 260GB | 58.5 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 = 400B × 0.604 B/param (4.83 bits) + 0.197 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.5 ÷ (17B active × 0.604 B/param) = 10.3 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.