Cheapest box to run gpt-oss-120b at Q8_0
OpenAI’s gpt-oss-120b is 117B parameters, 5.1B 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.
gpt-oss-120b at Q8_0 needs 126GB.
Cheapest Config that fits: Mac Studio, M3 Ultra, 256GB, refurbished. Fits, 122GB headroom. Est. 75.6 tok/s.
Best offer today: $7,729 at Apple Certified Refurbished — in stock, checked 2 hours ago.
Price history: 46 days recorded.
Offers — Mac Studio, M3 Ultra, 256GB, 1TB, refurbished
- Apple Certified RefurbishedRefurbished by Apple, with Apple's one-year limited warranty and 14-day returns. Apple says refurbished supply is usually very limited and often runs out, so this row can go dead faster than a new one.in stockchecked 2 hours ago$7,729
- Mac mini, M6, 16GB$1,099Won't fit−113GB headroom
- Mac mini, M6, 24GB$1,299Won't fit−105GB headroom
- Mac mini, M6, 32GB$1,499Won't fit−97GB headroom
- Mac mini, M5 Pro, 24GB$1,699Won't fit−105GB headroom
- Mac mini, M5 Pro, 48GB$2,499Won't fit−82GB headroom
- Mac Studio, M5 Max, 36GB$2,499Won't fit−93GB headroom
- Mac mini, M5 Pro, 64GB$2,899Won't fit−67GB headroom
- GeForce RTX 5090, 32GB$2,999.99+hostWon't fit−95GB headroom
- Won't fit−67GB headroom
- Mac Studio, M5 Max, 48GB$3,099Won't fit−82GB headroom
- Mac Studio, M5 Max, 64GB$3,499Won't fit−67GB headroom
- Won't fit−6GB headroom
- Won't fit−38GB headroom
- Won't fit−6GB headroom
- Won't fit−6GB headroom
- Won't fit−6GB headroom
- Won't fit−38GB headroom
- Fits122GB headroomest. 75.6 tok/s
- Fits122GB headroomest. 111 tok/s
- Fits378GB headroomest. 111 tok/s
| Config | Memory | Price | Fit | Headroom | Est. speed |
|---|---|---|---|---|---|
| Mac mini, M6 | 16GB | $1,099 | Won't fit | −113GB | — |
| Mac mini, M6 | 24GB | $1,299 | Won't fit | −105GB | — |
| Mac mini, M6 | 32GB | $1,499 | Won't fit | −97GB | — |
| Mac mini, M5 Pro | 24GB | $1,699 | Won't fit | −105GB | — |
| Mac mini, M5 Pro | 48GB | $2,499 | Won't fit | −82GB | — |
| Mac Studio, M5 Max | 36GB | $2,499 | Won't fit | −93GB | — |
| Mac mini, M5 Pro | 64GB | $2,899 | Won't fit | −67GB | — |
| GeForce RTX 5090 | 32GB | $2,999.99+host | Won't fit | −95GB | — |
| Mac Studio, M4 Max, refurb | 64GB | $3,049 | Won't fit | −67GB | — |
| Mac Studio, M5 Max | 48GB | $3,099 | Won't fit | −82GB | — |
| Mac Studio, M5 Max | 64GB | $3,499 | Won't fit | −67GB | — |
| Ascent GX10, GB10 Grace Blackwell | 128GB | $3,999.99 | Won't fit | −6GB | — |
| Mac Studio, M3 Ultra, refurb | 96GB | $4,329 | Won't fit | −38GB | — |
| Mac Studio, M4 Max, refurb | 128GB | $4,409 | Won't fit | −6GB | — |
| DGX Spark, GB10 Grace Blackwell | 128GB | $4,699 | Won't fit | −6GB | — |
| Mac Studio, M5 Max | 128GB | $5,099 | Won't fit | −6GB | — |
| Mac Studio, M5 Ultra | 96GB | $5,499 | Won't fit | −38GB | — |
| Mac Studio, M3 Ultra, refurb | 256GB | $7,729 | Fits | 122GB | 75.6 tok/s |
| Mac Studio, M5 Ultra | 256GB | $9,499 | Fits | 122GB | 111 tok/s |
| Mac Studio, M5 Ultra | 512GB | — | Fits | 378GB | 111 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 = 117B × 1.063 B/param (8.5 bits) + 0.074 GB/1K × 8K K/V + 1.2 GB runtime
speed = bandwidth × 0.5 ÷ (5.1B active × 1.063 B/param) = 5.4 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 M3 Ultra 256GB refurb runs
- Qwen3-Coder-480B-A35B-InstructQ3_K_M, est. 23.9 tok/s
- Llama-4-Maverick-17B-128EQ4_K_M, est. 39.9 tok/s
- GLM-4.6Q4_K_M, est. 21.2 tok/s
- DeepSeek-V4-FlashQ6_K, est. 38.4 tok/s
- Qwen3-235B-A22BQ6_K, est. 22.7 tok/s
- MiniMax-M2Q8_0, est. 38.5 tok/s
Best quant that still fits at 8K context, largest model first. Full list on the Config page.
Bandwidth 819GB/s, usable memory 248GB of 256GB.