Cheapest box to run Mistral-Large-2411 at Q8_0
Mistral’s Mistral-Large-2411 is 123B 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.
Mistral-Large-2411 at Q8_0 needs 135GB.
Cheapest Config that fits: Mac Studio, M5 Ultra, 256GB. Fits, 113GB headroom. Est. 6.0 tok/s.
Best offer today: $9,499 at Apple — in stock, checked 10 hours ago.
Collecting price history — 2 of 90 days. No timing verdict yet.
Offers — Mac Studio, M5 Ultra, 256GB, 1TB
- Mac mini, M6, 16GB$1,099Won't fit−122GB headroom
- Mac mini, M6, 24GB$1,299Won't fit−114GB headroom
- Mac mini, M6, 32GB$1,499Won't fit−106GB headroom
- Mac mini, M5 Pro, 24GB$1,699Won't fit−114GB headroom
- Mac mini, M5 Pro, 48GB$2,499Won't fit−91GB headroom
- Mac Studio, M5 Max, 36GB$2,499Won't fit−102GB headroom
- Mac mini, M5 Pro, 64GB$2,899Won't fit−76GB headroom
- GeForce RTX 5090, 32GB$2,999.99+hostWon't fit−104GB headroom
- Mac Studio, M5 Max, 48GB$3,099Won't fit−91GB headroom
- Mac Studio, M5 Max, 64GB$3,499Won't fit−76GB headroom
- Won't fit−14GB headroom
- Won't fit−14GB headroom
- Won't fit−15GB headroom
- Won't fit−46GB headroom
- Fits113GB headroomest. 6.0 tok/s
- Fits369GB headroomest. 6.0 tok/s
| Config | Memory | Price | $/GB | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | $69 | Won't fit | −122GB | — |
| Mac mini, M6 | 24GB | $1,299 | $54 | Won't fit | −114GB | — |
| Mac mini, M6 | 32GB | $1,499 | $47 | Won't fit | −106GB | — |
| Mac mini, M5 Pro | 24GB | $1,699 | $71 | Won't fit | −114GB | — |
| Mac mini, M5 Pro | 48GB | $2,499 | $52 | Won't fit | −91GB | — |
| Mac Studio, M5 Max | 36GB | $2,499 | $69 | Won't fit | −102GB | — |
| Mac mini, M5 Pro | 64GB | $2,899 | $45 | Won't fit | −76GB | — |
| GeForce RTX 5090 | 32GB | $2,999.99+host | $94 | Won't fit | −104GB | — |
| Mac Studio, M5 Max | 48GB | $3,099 | $65 | Won't fit | −91GB | — |
| Mac Studio, M5 Max | 64GB | $3,499 | $55 | Won't fit | −76GB | — |
| Ascent GX10, GB10 Grace Blackwell | 128GB | $3,999.99 | $31 | Won't fit | −14GB | — |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | $37 | Won't fit | −14GB | — |
| Mac Studio, M5 Max | 128GB | $5,099 | $40 | Won't fit | −15GB | — |
| Mac Studio, M5 Ultra | 96GB | $5,499 | $57 | Won't fit | −46GB | — |
| Mac Studio, M5 Ultra | 256GB | $9,499 | $37 | Fits | 113GB | 6.0 tok/s |
| Mac Studio, M5 Ultra | 512GB | — | — | Fits | 369GB | 6.0 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 = 123B × 1.063 B/param (8.5 bits) + 0.360 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.65 ÷ (123B active × 1.063 B/param) = 130.7 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 256GB runs
- Llama-4-Maverick-17B-128EQ4_K_M, est. 58.5 tok/s
- Qwen3-235B-A22BQ6_K, est. 33.3 tok/s
- Mistral-Large-2411Q8_0, est. 6.0 tok/s
- gpt-oss-120bBF16, est. 58.8 tok/s
- Llama-4-Scout-17B-16EBF16, est. 17.6 tok/s
- Llama-3.3-70BBF16, est. 5.6 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 248GB of 256GB.