HyphenTech · Field notes

HyphenTech · All posts

Page 4 of 6 · 21 posts per page. There's more to read. Glad you're here.

Back to home →
Can the Local 27B Model Operate Blender? I brought Bilibili's method into LocalBrain and ran it five times
Can the Local 27B Model Operate Blender? I brought Bilibili's method into LocalBrain and ran it five times

Using local Qwen3.8-27B modeling with blender-mcp, then testing it in LocalBrain for five rounds: the model can be done step by step, but slowly; The delivered black map is just one checkbox short; if it's not visible, it counts as complete, and only after viewing the final render can you use the correct modification.

Read more
Which local models can 8GB run? I tested 11 models, and 6 can fit in 8K context
Which local models can 8GB run? I tested 11 models, and 6 can fit in 8K context

Bringing 11 low-memory local models released this year to the local machine, using LocalBrain's built-in llama.cpp unified memory, speed, and tool calls: 6 under 8K context are within the default limit of 8GB devices. Qwen3.5-9B takes up 3GB less than last year's Qwen3-8B, and 27B of 1-bit can run but only has manufacturer numbers. This batch of models has also been added to LocalBrain's discovery page.

Read more
llama.cpp 0.4:64GB Is the hard wall loose?
llama.cpp 0.4:64GB Is the hard wall loose?

llama.cpp 0.4 rewrote the memory boundaries of large models with lazy loading, streaming quantization, and Apple RDMA. But LocalBrain's 64GB Mac records prove that a file larger than memory can boot, but that doesn't mean long contexts can run at full speed.

Read more
Is local AI safe just by opening localhost?
Is local AI safe just by opening localhost?

Just listening to 127.0.0.1 doesn't mean browsers can't encounter it. Three recent official security announcements plus a set of completely isolated CORS tests break down the most easily misunderstood security boundaries of local AI.

Read more
GPT-6 is here—is it really starting to work for you?
GPT-6 is here—is it really starting to work for you?

The real change in GPT-6 Astra isn't just a slight increase in chat score, but the simultaneous integration of computer operation, long tasks, and high-risk capabilities into the product. This article breaks down the available range, API costs, security boundaries, and how ordinary people choose based on OpenAI's official materials.

Read more
8 GB VRAM can run local AI: How to choose between Windows and Mac?
8 GB VRAM can run local AI: How to choose between Windows and Mac?

Instead of discussing superficial questions like "Is there a Windows version of the software?", let's answer two practical questions: which local models and tools can run on an 8 GB NVIDIA graphics card, and what makes the Mac's unified memory and complete multimedia chain strong.

Read more
DeepSeek Visual Open Source—Can a 64GB Mac Run It?
DeepSeek Visual Open Source—Can a 64GB Mac Run It?

DeepSeek turns vision into the Agent's perception entry point and opens up a 305B weight. The latest minimum visual GGUF is still about 67.8GiB: 64GB Mac is not suitable for stable deployment today. This article is based on official data and files, and does not use local running impersonation.

Read more
Fable 5.1 didn't drop in price, so why save 45%?
Fable 5.1 didn't drop in price, so why save 45%?

Fable 5.1 and Mythos 5.1 are the same underlying model, but were split into public and trusted access versions. The base unit price hasn't dropped, but cache reads are 75% cheaper; What truly changes are the task economics, security boundaries, and access methods for long-term agents.

Read more