AI Agents, Full Stack Developer, Open Source Contributor
Joined September 2020
- Tweets804
- Following74
- Followers156
- Likes643
RajuGangitla retweeted
Today, we’re announcing Ternary Bonsai 2 27B.
Based on Qwen3.8 27B, Bonsai 2 27B is 9x smaller than its full-precision counterpart while retaining 98.2% of its aggregate benchmark performance.
Two months after the first Bonsai 27B release, the biggest change is quality. The footprint remains 5.9 GB, but the gap to full precision has narrowed materially, with particularly strong gains in agentic coding, multimodal reasoning, and long-horizon tool use.
Ternary Bonsai 2 27B is available today under Apache 2.0.
Please give option to toggle on/off 5hr limit
@thsottiaux
If you want your Nextjs page to load faster, start here:
1. Open the Network tab and download the HAR file.
2. Run the @nextjs Turbopack Bundle Analyzer.
3. Give both to Claude and ask it to optimize the app.
That’s pretty much it. That’s what I did.
My dashboard went from 21s → 3s in production. 🚀
RajuGangitla retweeted
With Fable 5.1 out today, we've also reset 5-hour and weekly limits for all users.
2 rtx 5090
Still i need one more 😭😭
Qwen3.8-Flash can now be run locally! 🔥
The 125B MoE model outperforms Claude-Opus-4.6 (Max).
Run on 75GB RAM via Unsloth GGUFs.
Qwen3.8-Flash-Next enables CPU RAM / unified mem setups to deliver near VRAM speeds.
Guide: unsloth.ai/docs/models/qwen3…
GGUF: huggingface.co/unsloth/Qwen3…
RajuGangitla retweeted
Introducing GLM-5.3-Flash
- Leading capabilities at a highly competitive price
- Natively multimodal with a 1M-token context window
- A 320B-A18B model released under the MIT License
- Previously previewed as Ox Alpha, running entirely on Chinese AI chips
Blog: z.ai/blog/glm-5.3-flash
Available now across all official platforms:
Weights: huggingface.co/zai-org/GLM-5…
API: docs.z.ai/guides/llm/glm-5.3…
Coding Plan: z.ai/subscribe
ZCode: zcode.z.ai/en
Chat: chat.z.ai
AutoClaw: autoclaw.z.ai
RajuGangitla retweeted
⚡Meet Qwen3.8-Flash, a multimodal MoE and an early preview of the Qwen4 architecture, now open-weight!
The production version Qwen3.8-Flash will be available soon via QwenCloud API at just $ 0.16/1M input tokens and $ 0.47/1M output tokens.
125B parameters + 51B N-gram embeddings, with just 6B activated per token. Unmatched cost-efficiency.
What's new: 🥳
- Next architecture: GDN + QSA hybrid attention, Gated Residual, N-gram Embedding & Muon optimizer, serving as a precursor to the architecture used in Qwen4.
- Dramatically lower training and inference costs: trained at just 1/9 the cost of Qwen3.7-Plus, while outperforming it across the board with especially strong gains in coding and office tasks.
- Strong performance: scoring 58.7 on DeepSWE 1.1, 62.5 on SWE-bench Pro, 73.9 on CoWorkBench, 84.5 on AndroidWorld, and 95.7 on MathVision (with CI).
- 262K native context, extensible to 1M with YaRN.
We’re also releasing the weights for Qwen3.8-Flash-Next, giving the community an early look at the new architecture we’re exploring for Qwen4.🚀
We can't wait to see what you build with Qwen3.8-Flash!👀👇
- Blog: qwen.ai/blog?id=qwen3.8-flas…
- Technical Report: github.com/QwenLM/Qwen3.8-Fl…
- Hugging Face: huggingface.co/Qwen/Qwen3.8-…
- ModelScope: modelscope.cn/models/Qwen/Qw…
