cd /news/large-language-models/qwen-3-8-flash-via-dwarfstar · home topics large-language-models article
[ARTICLE · art-129186] src=twitter.com ↗ pub= topic=large-language-models verified=true sentiment=↑ positive

Qwen 3.8 Flash via DwarfStar

Salvatore Sanfilippo (antirez) announced that Qwen3.8 Flash Next is now supported in DwarfStar, delivering 50–70 tokens per second inference and over 1400 tokens per second prefill on 64GB Mac systems, Metal-only for now. Sanfilippo credited contributor @ivanfioravanti for the pull request and noted N-grams on SSD as in DS4.1F, adding that the speed could appeal to DGX Spark users with 128GB and that ROCm makes sense for 64GB Framework Desktop owners.

read1 min views3 publishedSep 14, 2026
Qwen 3.8 Flash via DwarfStar
Image: source

antirez on X: "Qwen3.8 Flash Next is now supported in DwarfStar, covering 64GB Mac systems very well and with very fast inference of 50~70 t/s and > 1400 t/s prefill. For now this is Metal only. Thanks to @ivanfioravanti for all the cool work in the PR. N-grams on SSD like for DS4.1F."

Qwen3.8 Flash Next is now supported in DwarfStar, covering 64GB Mac systems very well and with very fast inference of 50~70 t/s and > 1400 t/s prefill. For now this is Metal only. Thanks to @ivanfioravanti for all the cool work in the PR. N-grams on SSD like for DS4.1F.

Qwen3.8 Flash Next is now supported in DwarfStar, covering 64GB Mac systems very well and with very fast inference of 50~70 t/s and > 1400 t/s prefill. For now this is Metal only. Thanks to @ivanfioravanti for all the cool work in the PR. N-grams on SSD like for DS4.1F.

Not sure if this makes sense on the DGX Spark. You have 128GB there, however the extra speed could be very tempting for the Spark users, as well as having a lot of RAM free for other stuff. For ROCm it makes sense as many folks have a Framework Desktop with 64GB.

── more in #large-language-models 4 stories · sorted by recency
── more on @qwen3.8 flash next 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/qwen-3-8-flash-via-d…] indexed:0 read:1min 2026-09-14 ·