Type: AI model or model family
Qwen3.8 appears in the radar stream as a model or model family. This page is a living index of dated mentions and sources — open Recent Updates and Backlinks for context, not a full product brief.
Recent Updates
- 2026-08-12: Qwen3.8-2.4T-A95B-FP8: Open-Source FP8-Quantized Model Release (Hacker News) · huggingface.co — Open Source LLMs Alibaba · Hugging Face Qwen3.8-2.4T-A95B-FP8 · Qwen3.8-Max · Qwen3.5 · Qwen3.6
- 2026-08-29: Why Local LLM Deployments Produce Different Results: Inference Stack Variations and Numerical Drift (breakingnewsofficial) · qbitai.com — Open Source LLMs Agents Tool Use Long Context NVIDIA · Hugging Face thr3e · Qwen3.6-27B
- 2026-08-29: vLLM v0.28.0: Major optimizations for Kimi-K3 and DeepSeek V4, expanded model support (breakingnewsofficial) · github.com — Open Source LLMs DeepSeek · AMD · NVIDIA · Google · Hugging Face buf · Kimi K3 · DeepSeek V4 · Qwen3.5 · Qwen3-VL Mistral-Large-3 · Gemma4 Keye Ultravox · Muse Glimmer Ling-3.0-Flash Dots3 Interns2mobius Ernie-4.5-VL
- 2026-09-08: Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses (breakingnewsofficial) · quesma.com — Open Source LLMs Code Agents LLM Evals Unsloth · Modal · Qwen3.6 · Opus 4.7 · Gemini-3.1-Pro
FAQ
What is Qwen3.8?
Qwen3.8 appears in the radar stream as a model or model family. This page is a living index of dated mentions and sources — open Recent Updates and Backlinks for context, not a full product brief.
What does this page track?
Dated radar mentions, source links, related concepts, and builder-relevant context for Qwen3.8, collected automatically by GROUNDING.
When was Qwen3.8 last mentioned?
Qwen3.8 was most recently mentioned in a radar update dated 2026-09-08.
Category: Text / Language Models