Sunk Cost sunkcost.ai Data checked 2026-09-03

What hardware do you need to run Qwen3.8 Flash Next?

Qwen3.8 Flash Next at Q4_K_M is 120 GB of weights, with a context ceiling of 256k tokens. Not yet rated: released after our last ratings pass. The strongest open model that fits in 128 GB, and the only one within reach of the hosted mid-tier.

Cheapest machine that runs itMac Studio M5 Ultra, 256GB at $10,799
Fastest of the ones listedMac Studio M5 Ultra, 256GB — 74 tok/s at 32k context
Honest answer on costPays back in 372 years at 500k tokens a day.

How good is it, really?

On the Artificial Analysis Intelligence Index v4.3 it scores 40, which puts it in the Sonnet-class band. In the same league as the labs' mainstream models on this index. Score source. See the whole table.

What it costs either way

Renting the same model costs $0.15 per million input tokens and $0.47 per million output (OpenRouter, cheapest active endpoint, checked 2026-09-09). Buying a machine only beats that if you use it hard enough, for long enough, that the hardware price divides down below the rental bill.

Machines that run it

MachinePriceSpeed at 32kPay-back
Mac Studio M5 Ultra, 256GB $10,799 74 tok/s estimated Pays back in 372 years Run the numbers

One machine per family, cheapest first. Speeds are measured where a public benchmark exists and estimated from memory bandwidth otherwise; the calculator says which for any configuration.

The specifics

Parameters
180B, of which 6B are active per token
Quantisation
Q4_K_M
Weights on disk
120 GB
KV cache
0.9 GB at 32k context — Hybrid: 12 of 48 layers hold a growing cache, and each also runs a sparse-attention indexer with its own cache, adding about 12% on top of the plain figure.
Maximum context
256k tokens (256k)
Licence
qwen-community-1.0
Sources
source 1