Tag feed

#qwen

93 posts0 followers

Explore Hashnode

Alternatives

Trending tags this week

Mmamonumamonu.hashnode.dev16h ago · 10 min read

Running a A 27B Model in 3.5 GB VRAM

Bonsai-27B-gguf is Qwen3.6-27B with every weight stored as a single bit. The file is 3.5 GB and it fits on an 8 GB GPU. FP16 weights for a 27B model are about 54 GB. A conventional 4-bit GGUF is about

0

NNickblog.gpus.marketAug 14 · 9 min read

Deploying Qwen3.8-2.4T-A95B with vLLM: Verified GPU Pods, Quants, and Serving Recipes

Qwen3.8-2.4T-A95B is a 2.4-trillion-parameter Mixture-of-Experts model with roughly 95B parameters active for each token. If you're planning to self-host it, the first thing to know is that this is a

1

T

MAMuhammad Azlaan Zubairblog.mdazlaanzubair.comAug 8 · 16 min read

Claude’s Intelligence Isn’t Worth $20 to Me Anymore

I like Claude. That is precisely why I have a problem with Claude Pro. Claude can write exceptionally well. Its coding models are genuinely competitive. Claude Code is one of the strongest arguments

4

TTD

DSDarsh Shahfreecodecamp.orgAug 6 · 16 min read

How to Customize an LLM for AI Agents using SFT and QLoRA

In this tutorial, I’ll show you how to fine-tune a large language model for use in AI agents using supervised fine-tuning with QLoRA. This lets us customize a pre-trained model so it behaves the way w

0

AGAditi Guptahonestaireview.hashnode.devAug 4 · 8 min read

Qwen3.8-Max Beat Claude

Alibaba has released Qwen3.8-Max, its largest and most capable AI model to date. The headline specifications are absurd: 2.4 trillion total parameters, 95 billion activated per token, multimodal input

0

MSManu Shuklaecorpit.hashnode.devAug 4 · 16 min read

Qwen3.8-Max went GA on 3 August 2026 at $2 and $6 per million tokens, and it is more expensive than Qwen3.7-Max is today

Qwen3.8-Max went GA on 3 August 2026 at $2 and $6 per million tokens, and it is more expensive than Qwen3.7-Max is today Summary. Alibaba's Qwen team made Qwen3.8-Max generally available on 3 August

0

VAVoor Aivooraihowto.hashnode.devAug 1 · 3 min read

How to Use Qwen Image Edit With a Pixel-Diff Validation Mask

Qwen Image Edit is most reliable when an edit is treated as a bounded patch, not a request to “improve” the entire image. Define the allowed change region, list the invariants, run the edit, and compa

0

MSManu Shuklaecorpit.hashnode.devJul 31 · 15 min read

Qwen3.7 Flash vs Gemini 3.5 Flash-Lite: the 2026 cost math for 1M-context vision agents

Qwen3.7 Flash vs Gemini 3.5 Flash-Lite: the 2026 cost math for 1M-context vision agents Summary. Alibaba released Qwen3.7 Flash on 27 July 2026 at $0.03 per million input tokens and $0.13 per millio

0

DSDarsh Shahfreecodecamp.orgJul 24 · 11 min read

How to Use Prompt Engineering and Context Engineering for AI Agents

In this tutorial, I’ll show you how prompt engineering and context engineering can improve an AI agent's performance. We’ll build a simple local agent, start with a baseline input, then improve it wit

0

YFYuki Furutablog.yukifuruta.comJul 22 · 24 min read

Running Edge LLMs on a Raspberry Pi

What if a Raspberry Pi could generate text entirely on its own, without sending prompts to a cloud-based AI service? To find out, I installed several compact large language models on a Raspberry Pi 5

0

#qwen

Search Hashnode

#qwen

Explore Hashnode

Trending tags this week

Running a A 27B Model in 3.5 GB VRAM

Deploying Qwen3.8-2.4T-A95B with vLLM: Verified GPU Pods, Quants, and Serving Recipes

Claude’s Intelligence Isn’t Worth $20 to Me Anymore

How to Customize an LLM for AI Agents using SFT and QLoRA

Qwen3.8-Max Beat Claude

Qwen3.8-Max went GA on 3 August 2026 at $2 and $6 per million tokens, and it is more expensive than Qwen3.7-Max is today

How to Use Qwen Image Edit With a Pixel-Diff Validation Mask

Qwen3.7 Flash vs Gemini 3.5 Flash-Lite: the 2026 cost math for 1M-context vision agents

How to Use Prompt Engineering and Context Engineering for AI Agents

Running Edge LLMs on a Raspberry Pi