Qwen3.6 35B-A3B vs Muse Glimmer 30B
Qwen3.6 35B-A3B scores higher on the intelligence index, 19 against 18. Both take the same machine to start: the cheapest here that runs either is the Framework Desktop, 32GB, at $1,269. On it, Qwen3.6 35B-A3B is about 5.1× quicker: 56 tok/s against 11, both estimated from memory bandwidth. At 500k tokens a day the Framework Desktop, 32GB pays for itself in 22 years running Muse Glimmer 30B, against 83 years running Qwen3.6 35B-A3B.
| Qwen3.6 35B-A3B | Muse Glimmer 30B | |
|---|---|---|
| Intelligence index | 19 | 18 |
| Class | Haiku-class | Haiku-class |
| Weights | 22 GB | 17 GB |
| Needs at 32k | 23 GB | 18 GB |
| Quantisation | Q4_K_M | Q4_K_M |
| Parameters | 36B (3B active) | 29.8B |
| Max context | 256k | 128k |
| API price per 1M | $0.05 in / $0.7 out | $0.3 in / $1.2 out |
| Licence | Apache 2.0 | Apache 2.0 |
| Machines here that run it | 28 of 37 | 30 of 37 |
| Cheapest machine that runs it | Strix Halo Framework Desktop, 32GB $1,269 | Strix Halo Framework Desktop, 32GB $1,269 |
Run Qwen3.6 35B-A3B on the Framework Desktop, 32GB · or Muse Glimmer 30B
Jump to: Side by side on the Framework Desktop, 32GB · How much use it takes to pay for the machine · Machines that run one and not the other · The assumptions behind both columns
Side by side on the Framework Desktop, 32GB
The cheapest machine that runs either model is the same one, so this is the pair doing the same work on the same hardware: Strix Halo Framework Desktop, 32GB, at $1,269.
| Qwen3.6 35B-A3B | Muse Glimmer 30B | |
|---|---|---|
| Speed at 32k | 56 tok/s estimated | 11 tok/s estimated |
| Pay-back on this machine | Pays back in 83 years | Pays back in 22 years |
| API cost per month | $1.38 | $5.42 |
Run Qwen3.6 35B-A3B on the Framework Desktop, 32GB · or Muse Glimmer 30B
How much use it takes to pay for the machine
Everything above is at 500k tokens a day. Pay-back moves with how much you actually run, so here are both models at the five levels of use the calculator names, on the Framework Desktop, 32GB. Muse Glimmer 30B pays for it sooner at every level of use, so which of them to run does not turn on how hard you work it.
| A day's use | Qwen3.6 35B-A3B | Muse Glimmer 30B |
|---|---|---|
| 50ka few chats a day | 831 years | 217 years |
| 200klight assistant use | 208 years | 54 years |
| 1Ma moderate coding-assistant day | 42 years | 11 years |
| 4Mheavy coding with an agent | 10 years | 2.7 years |
| 20Magents running most of the day | 2.1 years | 8.8 monthsits ceiling |
The Framework Desktop, 32GB generates at most 14.9M tokens a day on Muse Glimmer 30B, so that column's figure at 20M tokens a day is for the most it can do, not for the whole of what was asked.
Run Qwen3.6 35B-A3B at 20M tokens a day · or Muse Glimmer 30B
Machines that run one and not the other
Muse Glimmer 30B needs 18 GB of memory at 32k of context and Qwen3.6 35B-A3B needs 23 GB. That puts Muse Glimmer 30B on 2 of the 37 machines priced here that Qwen3.6 35B-A3B does not, starting at $1,299.
| Machine | Price | Memory | Speed on Muse Glimmer 30B | Pay-back |
|---|---|---|---|---|
| Mac mini M6, 32GB | $1,299 | 32 GB | 7.2 tok/s estimated | Pays back in 22 years |
| MacBook Pro M5 (14-inch), 32GB | $2,399 | 32 GB | 6.4 tok/s estimated | Pays back in 40 years |
Qwen3.6 35B-A3B is also head to head with Nemotron 3.5 Bolt 74B-A9B above it on the leaderboard. One more model needs much the same memory: Gemma 4 31B it. Muse Glimmer 30B is also head to head with Gemma 4 26B-A4B below it on the leaderboard. One more model needs much the same memory: Qwen3.8 27B.
The assumptions behind both columns
Both columns use the same usage: 500k tokens a day at 15:1 input to output, 32k of context, $0.17 per kWh, and today's API prices held flat. Speeds marked estimated are worked out from memory bandwidth rather than measured, and pay-back scales with them. Where nobody rents an open model by the token, its API prices are the nearest hosted model's, named beside them. Machines are the 37 here with a published price that are still sold. Change any of it in the calculator.
More head to head: every machine that runs Qwen3.6 35B-A3B · every machine that runs Muse Glimmer 30B · every other match-up · both against the frontier · the quickest pay-back at each level of use