What hardware do you need to run Nemotron 3.5 Lightning 30B-A3B?
Nemotron 3.5 Lightning 30B-A3B at Q4_K_M is 25 GB of weights, with a context ceiling of 256k tokens. Not yet rated: released after our last ratings pass. NVIDIA's Mamba hybrid: almost no KV cache, so long contexts cost nothing in memory.
How good is it, really?
On the Artificial Analysis Intelligence Index v4.3 it scores 14, 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 $0.08 per million input tokens and $0.2 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
| Machine | Price | Speed at 32k | Pay-back | |
|---|---|---|---|---|
| Strix Halo Framework Desktop, 64GB | $1,959 | 54 tok/s estimated | Pays back in 134 years | Run the numbers |
| Mac mini M5 Pro, 48GB | $2,299 | 35 tok/s estimated | Pays back in 166 years | Run the numbers |
| Mac Studio M5 Max, 36GB | $2,499 | 53 tok/s estimated | Pays back in 172 years | Run the numbers |
| MacBook Pro M5 Pro (16-inch), 48GB | $3,599 | 35 tok/s estimated | Pays back in 260 years | Run the numbers |
| DGX Spark GB10 Grace Blackwell, 128GB | $4,699 | 68 tok/s estimated | Pays back in 318 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
- 31.6B, of which 3B are active per token
- Quantisation
- Q4_K_M
- Weights on disk
- 25 GB
- KV cache
- 0.2 GB at 32k context — Only 6 of 52 layers are attention at all; 23 are Mamba blocks with a fixed-size state and 23 are feed-forward only. The context is close to free.
- Maximum context
- 256k tokens (256k)
- Licence
- OpenMDW 1.1
- Sources
- source 1