Agree, and upvoted.

Another good size would be 160 gb for 96 gb vram systems. After that I would like to see 225 to 250 gb.

I hope an instruction tuned will be released as well.

Oh hell yeah

I'm on my 1070 8gb copium so we're twinsies

Maybe they release a huge moe model with non-uniform quants and then we can get even more quality on those cute little cards

I have an M4 Pro 24GB and I still use Gemma 26B-A4B as my primary model. Beats every other model I’ve ever tried locally on most stuff except coding and tool use, so a Qwen 4 at this size would be super interesting

What are the significant changes? Requiring attribution or something more sinister?

If they can make the KV cache size scale more efficiently with many tokens, like DeepSeek 4.1 Flash fitting 1 million tokens in 890MB, it might give them enough room to add a couple billion parameters of weights and still fit well in 32GB GPUs

Not necessarly, I'd say. We've seen many releases with multiple sizes and the 27B class has been around since at least the Gemma3 times.