Qwen3.8-Flash-Next
alibaba/qwen3.8-flash-next- Alibaba
- Family · Qwen3-Flash-Next
- Released 26 Aug 2026
Not on OSMEXO yet
Scores · standing
Intelligence39.8#35/489
Coding73.1#17/196
News & trends
74 mentions this week ▲ 139%this model · videos, posts, articles · 30 days
Trending · 14 days
- Run Qwen3.8-Flash-Next (125B) on FREE Kaggle GPUs 🚀 | Strata + OpenCode26.9K views
- Qwen3.8 Flash Next на RTX 3090: полноценная разработка без облака21.6K views
- Debunking Cohere's claim of Qwen 3.8 Flash Next uploading to Alibaba remote URL985 upvotes
- Alibaba's Qwen3.8-Flash-Next model tried to upload a file to Beijing in a test5 points
- Running Qwen3.8-Flash-Next NVFP4 at 184 tok/s on a single RTX 6000 Pro26 points
- I now have definitive proofs that my Qwen Flash Next is trying to send something to a remote Chinese server1.2K upvotes
- @cohere on X3.0M views
News
- Alibaba's Qwen3.8-Flash-Next model tried to upload a file to Beijing in a testnotebookcheck.net · 27 Oct
- Running Qwen3.8-Flash-Next NVFP4 at 184 tok/s on a single RTX 6000 Promeshapplied.com · 26 Oct
- sglang v0.5.22SGLang · 19 Oct
- sglang v0.5.20SGLang · 18 Sep
Benchmarks
bar = share of the top score · Benchmark data: Artificial AnalysisSpeed · median across providers, latest day
Output speed#87/10353 tok/s2.2× slower than median
First token#691.49 s1.6× longer than median
First answer token#8339 sthinking included
Research papers
- Evolving Agent Teams27 Oct
- HyScale: Scaling Long-Context Training for Learned Sparse Attention23 Oct
- Low-Bit N-Gram Embeddings for Language Models22 Oct
- Delta N-gram: Forward-Only Continual Writing into a Language Model's Native N-gram Memory22 Oct
- Uncensored Is Not Unbiased: Abliteration Removes Refusals but Not Script-Dependent Bias About Taiwan21 Oct
- FlashNext-RL: A System Optimization Study for Long-Horizon Agentic RL of Qwen3.8-Flash-Next20 Oct
- Where Is the "Self" of a Large Language Model? -- From Self-Index to Self-Reference12 Oct
- GateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMs10 Oct
Social
Most watched and discussed · 90 days
- Run Qwen3.8-Flash-Next (125B) on FREE Kaggle GPUs 🚀 | Strata + OpenCodeDevZoneX · 26.9K views · 28 Oct
- Qwen3.8 Flash Next на RTX 3090: полноценная разработка без облакаГалера Морева · 21.6K views · 27 Oct
- Qwen3.8-Flash-Next vs Qwen3.8-27B: Which Should You Run?DeepWakeLabs · 18.6K views · 21 Oct
- New Strata App: Qwen3.8-Flash-Next Q5 at 1M Context on M5 Max + Q2 on M6 Mac miniExecute Automation · 16.1K views · 20 Oct
- Qwen 3.8 Flash-Next vs Qwen 3.8 27B: Real World Test on 2,031 JobsNick Reese · 11.1K views · 29 Oct
- Strata Coder vs Qwen 3.8 Flash Next: 9 Real Tests. Insane Results!Lukasz Gawenda · 9.0K views · 25 Oct
- Qwen3.8 Flash Nextに不審な動作？現場ではいったい何が起きたのか【ローカルLLM #セキュリティ】ふじもったチャンネル · 4.9K views · 28 Oct
- Lean-QwenFlash: Qwen3.8-Flash-Next (125B Model) on 8GB of RAMAgenticEngineering · 4.4K views · 30 Oct
- Qwen 3.8 Flash Next vs 27B on a 2014 Server: Strata Makes It Faster. What Do You Lose?The Local Ceiling · 2.3K views · 26 Oct
- Strata - Битва квантов: Q4 vs NVFP4 vs FP4-Local - Qwen3.8-Flash-NextMrGips • LLM · 1.6K views · 31 Oct
- Qwen3.8-Flash-Next on an 8GB GPU at 262K Context: The Regex TrickAgenticEngineering · 1.5K views · 28 Oct
- Flash-Next vs Qwen 3.8 27B: almost 3x faster on a 64 GB MacHermit's Sandbox · 1.3K views · 26 Oct
Alternatives
other vendors · similar capability- 39.5
- 41.8
- 37.9
- 38.1
Want Qwen3.8-Flash-Next on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.