# Not Much of a Glimmer

> Source: <https://pac.commonsware.com/archive/not-much-of-a-glimmer/>
> Published: 2026-08-11 22:00:00+00:00

Meta recently released Muse-Glimmer, an open-weights/open source model sized for commodity hardware.

I downloaded the Ollama `muse-glimmer:30b-mxfp8-dflash`

edition onto my 64GB M2 Ultra Mac Studio. `mxfp8`

is a less-aggressive compression model than I usually employ on that machine (`nvfp4`

). `dflash`

uses a predictive algorithm to help improve speed, supposedly.

I then had Muse-Glimmer run the same documentation-review prompt that I had Qwen 3.6 run previously, covered in [my preceding issue](https://pac.commonsware.com/archive/2026-local-models-analysis-over-generation/). Muse-Glimmer ran more than twice as long and came up with a small fraction of what Qwen did.

Muse-Glimmer may have uses, but I suspect that few of those will tie into coding agents.

I might give NVIDIA's Nemotron 3.5 Lightning a shot, though NVIDIA's own benchmarks have it lower at coding tasks than Qwen 3.6.