What hardware do you need to run Qwen3-Coder Next?
Qwen3-Coder Next at Q4_K_M is 48 GB of weights, with a context ceiling of 256k tokens. Not yet rated: released after our last ratings pass. Qwen's current coding model: 80B on disk but only 3B active per token.
How good is it, really?
On the Artificial Analysis Intelligence Index v4.3 it scores 10, which puts it in the Below every hosted tier band. Fine for simple, well-specified tasks. Noticeably less capable than anything the big labs sell today. Score source. See the whole table.
- Summarising — not rated
- Translation — not rated
- Everyday coding — not rated
- Reasoning & maths — not rated
- Agentic work — not rated
What it costs either way
Renting the same model costs $0.12 per million input tokens and $0.8 per million output (OpenRouter, cheapest active endpoint, checked 2026-09-15). 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
| Machine | Price | Speed at 32k | Pay-back | |
|---|---|---|---|---|
| Strix Halo Framework Desktop, 128GB | $3,449 | 54 tok/s estimated | Pays back in 122 years | Run the numbers |
| DGX Spark GB10 Grace Blackwell, 128GB | $4,699 | 68 tok/s estimated | Pays back in 165 years | Run the numbers |
| Mac Studio M5 Max, 128GB | $5,099 | 70 tok/s estimated | Pays back in 179 years | Run the numbers |
| MacBook Pro M5 Max (16-inch), 128GB | $6,999 | 70 tok/s estimated | Pays back in 245 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
- 79.7B, of which 3B are active per token
- Quantisation
- Q4_K_M
- Weights on disk
- 48 GB
- KV cache
- 0.8 GB at 32k context — Hybrid: 12 of 48 layers hold a growing cache.
- Maximum context
- 256k tokens (256k)
- Licence
- Apache 2.0
- Sources
- source 1