BestHub
Sign in
Lao Guo's Learning Space
Author

Lao Guo's Learning Space

AI learning, discussion, and hands‑on practice with self‑reflection

126
Articles
0
Likes
1.6k
Views
0
Comments
Recent Articles

Latest from Lao Guo's Learning Space

100 recent articles max
Lao Guo's Learning Space
Lao Guo's Learning Space
Nov 2, 2026 · Artificial Intelligence

5×27B Qwen Agents Beat Fable 5 via Orchestration: Pipeline vs Single-Call Analysis

The article corrects a viral claim that five Qwen-72B agents beat Fable 5, revealing it was actually five Qwen3.8-27B models using a multi-agent orchestration (Memdoor team-solve) achieving 9.8 vs 8.0 on LiveCodeBench Hard, but clarifies this compares a 40-minute pipeline to a single call, with contamination concerns, and argues orchestration is a more cost-effective lever than model scale.

Agent workflowLiveCodeBenchMemdoor
0 likes · 11 min read
5×27B Qwen Agents Beat Fable 5 via Orchestration: Pipeline vs Single-Call Analysis
Lao Guo's Learning Space
Lao Guo's Learning Space
Nov 1, 2026 · Artificial Intelligence

Two RTX 3090s Hit 3145 tok/s on 180B Model: Strata Engine Brings Giant LLMs to Gaming PCs

The Strata inference engine enables Qwen3.8-Flash-Next (180B total params, 6B active) to achieve 3145 tokens/sec prefill and 120 tokens/sec decode at 400K context on dual RTX 3090s by offloading experts to CPU/SSD, using speculative decoding and chunked prefill, offering a low-cost alternative to Mac Studio for long-context workloads.

LLM inferenceQwen3.8-Flash-NextRTX 3090
0 likes · 11 min read
Two RTX 3090s Hit 3145 tok/s on 180B Model: Strata Engine Brings Giant LLMs to Gaming PCs
Lao Guo's Learning Space
Lao Guo's Learning Space
Nov 1, 2026 · Artificial Intelligence

Zero-Edit Daily Short Videos: Automate Hot-Topic Clips with WorkBuddy & MiniMax H3

The article details a six-step automated workflow for generating daily short videos from trending topics using scheduled triggers, hot-topic fetching, PIL-rendered frames to avoid Chinese text garbling, and MiniMax H3 image-to-video generation, enabling creators to publish three times daily without manual editing.

MiniMax H3PILWorkBuddy
0 likes · 8 min read
Zero-Edit Daily Short Videos: Automate Hot-Topic Clips with WorkBuddy & MiniMax H3
Lao Guo's Learning Space
Lao Guo's Learning Space
Oct 31, 2026 · Artificial Intelligence

GPT-6.1 Terra Price Halved: Cloud vs Local Mac LLM Cost Breakdown

The article analyzes OpenAI's GPT-6.1 Terra price cut to $1/$5 per million tokens, reveals a 272K token billing trap, and compares cloud API costs against local Mac deployment (M5 Ultra 256GB), finding a break-even at ~92M tokens/month, while noting Terra's closed-source nature prevents local execution, making open-source alternatives like DeepSeek V4.1 Flash and Qwen3.8 better for privacy, fine-tuning, and offline use.

DeepSeek-V4.1-FlashGPT-6.1 TerraLLM pricing
0 likes · 9 min read
GPT-6.1 Terra Price Halved: Cloud vs Local Mac LLM Cost Breakdown
Lao Guo's Learning Space
Lao Guo's Learning Space
Oct 31, 2026 · Artificial Intelligence

GLM-5.3 Flash vs DeepSeek-V4.1 Flash: 20% Faster Code Gen on M5 Ultra

Benchmark comparison of GLM-5.3 Flash and DeepSeek-V4.1 Flash on Mac Studio M5 Ultra 256GB shows GLM-5.3 Flash achieves 84.9 vs 71.2 tok/s in code decoding (1.2x), 109.2 vs 93.6 tok/s in 8-request concurrency, and mixed first-token latency results across 16K-128K contexts, with caveats about different inference engines and no quality evaluation.

DeepSeek-V4.1-FlashGLM-5.3 FlashMac Studio M5 Ultra
0 likes · 8 min read
GLM-5.3 Flash vs DeepSeek-V4.1 Flash: 20% Faster Code Gen on M5 Ultra
Lao Guo's Learning Space
Lao Guo's Learning Space
Oct 31, 2026 · Artificial Intelligence

552B DeepSeek on M5 Ultra 256GB: 3883 Prefill, 92 Decode Tok/s – Local Full-Scale LLM Achieved

Community developers benchmarked the 552B DeepSeek V4.1-Flash model at 3bpw quantization on a Mac Studio M5 Ultra with 256GB unified memory, achieving 3883 tok/s prefill, 92 tok/s decode, and up to 163 tok/s with speculative decoding, demonstrating that full-scale LLMs can run locally on consumer hardware.

Apple SiliconDeepSeekLLM inference
0 likes · 8 min read
552B DeepSeek on M5 Ultra 256GB: 3883 Prefill, 92 Decode Tok/s – Local Full-Scale LLM Achieved
Lao Guo's Learning Space
Lao Guo's Learning Space
Oct 30, 2026 · Industry Insights

Rubin Mass Production: 960K GPUs, 800V Cooling — Why Your Mac Isn't Obsolete

NVIDIA's Rubin platform enters mass production with 960,000 GPUs deployed at Google Cloud using 800V liquid cooling, delivering 10x performance-per-watt over Blackwell, but the article argues local Macs remain valuable for small-model inference while Rubin targets industrial-scale AI factories, outlining three user paths based on needs.

800V DCAI factoryAI infrastructure
0 likes · 12 min read
Rubin Mass Production: 960K GPUs, 800V Cooling — Why Your Mac Isn't Obsolete