Cheapest box to run GLM-4.6 at Q6_K
Z.ai’s GLM-4.6 is 357B parameters, 32B 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.
GLM-4.6 at Q6_K needs 297GB.
Cheapest Config that fits: Mac Studio, M5 Ultra, 512GB. Fits, 207GB headroom. Est. 22.9 tok/s.
No price yet: Ships late October 2026. Apple has not published a price.
Collecting price history — 3 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−284GB headroom
- Mac mini, M6, 24GB$1,299Won't fit−276GB headroom
- Mac mini, M6, 32GB$1,499Won't fit−268GB headroom
- Mac mini, M5 Pro, 24GB$1,699Won't fit−276GB headroom
- Mac mini, M5 Pro, 48GB$2,499Won't fit−253GB headroom
- Mac Studio, M5 Max, 36GB$2,499Won't fit−264GB headroom
- Mac mini, M5 Pro, 64GB$2,899Won't fit−238GB headroom
- GeForce RTX 5090, 32GB$2,999.99+hostWon't fit−266GB headroom
- Won't fit−238GB headroom
- Mac Studio, M5 Max, 48GB$3,099Won't fit−253GB headroom
- Mac Studio, M5 Max, 64GB$3,499Won't fit−238GB headroom
- Won't fit−177GB headroom
- Won't fit−209GB headroom
- Won't fit−177GB headroom
- Won't fit−177GB headroom
- Won't fit−177GB headroom
- Won't fit−209GB headroom
- Won't fit−49GB headroom
- Won't fit−49GB headroom
- Fits207GB headroomest. 22.9 tok/s
| Config | Memory | Price | $/GB | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | $69 | Won't fit | −284GB | — |
| Mac mini, M6 | 24GB | $1,299 | $54 | Won't fit | −276GB | — |
| Mac mini, M6 | 32GB | $1,499 | $47 | Won't fit | −268GB | — |
| Mac mini, M5 Pro | 24GB | $1,699 | $71 | Won't fit | −276GB | — |
| Mac mini, M5 Pro | 48GB | $2,499 | $52 | Won't fit | −253GB | — |
| Mac Studio, M5 Max | 36GB | $2,499 | $69 | Won't fit | −264GB | — |
| Mac mini, M5 Pro | 64GB | $2,899 | $45 | Won't fit | −238GB | — |
| GeForce RTX 5090 | 32GB | $2,999.99+host | $94 | Won't fit | −266GB | — |
| Mac Studio, M4 Max, refurb | 64GB | $3,049 | $48 | Won't fit | −238GB | — |
| Mac Studio, M5 Max | 48GB | $3,099 | $65 | Won't fit | −253GB | — |
| Mac Studio, M5 Max | 64GB | $3,499 | $55 | Won't fit | −238GB | — |
| Ascent GX10, GB10 Grace Blackwell | 128GB | $3,999.99 | $31 | Won't fit | −177GB | — |
| Mac Studio, M3 Ultra, refurb | 96GB | $4,329 | $45 | Won't fit | −209GB | — |
| Mac Studio, M4 Max, refurb | 128GB | $4,409 | $34 | Won't fit | −177GB | — |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | $37 | Won't fit | −177GB | — |
| Mac Studio, M5 Max | 128GB | $5,099 | $40 | Won't fit | −177GB | — |
| Mac Studio, M5 Ultra | 96GB | $5,499 | $57 | Won't fit | −209GB | — |
| Mac Studio, M3 Ultra, refurb | 256GB | $7,729 | $30 | Won't fit | −49GB | — |
| Mac Studio, M5 Ultra | 256GB | $9,499 | $37 | Won't fit | −49GB | — |
| Mac Studio, M5 Ultra | 512GB | — | — | Fits | 207GB | 22.9 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 = 357B × 0.820 B/param (6.56 bits) + 0.377 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.5 ÷ (32B active × 0.820 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
- Kimi-K2-InstructQ3_K_M, est. 38.4 tok/s
- DeepSeek-V3Q5_K_M, est. 22.9 tok/s
- DeepSeek-R1Q5_K_M, est. 22.9 tok/s
- Qwen3-Coder-480B-A35B-InstructQ6_K, est. 20.9 tok/s
- Llama-4-Maverick-17B-128EQ8_0, est. 33.2 tok/s
- GLM-4.6Q8_0, 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.