Llama

For most of the LLM era the open-weight story was framed as a trailing one. Open models were cheaper, smaller, and a generation behind. That framing has not survived 2026. The gap between the best open-weight model and the best closed model is now narrow enough on most workloads that the choice is no longer “settle for less” - it is “decide what you actually need.” TL;DR Open weights have closed the headline gap. Top open-weight models are within striking distance of closed frontier models on reasoning, coding, and general knowledge benchmarks. The economics changed first. DeepSeek’s R1 made it credible that a frontier model could be trained for tens of millions, not billions - and that the weights could be released for free. Llama, Mistral, Qwen, and DeepSeek lead on different axes: Llama for broad ecosystem support, Mistral for European deployment and tool use, Qwen for multilingual and long-context work, DeepSeek for raw reasoning. Inference flexibility is the underrated win. Open weights mean you can run on your own hardware, fine-tune freely, and avoid surprises from a closed provider’s roadmap. The remaining closed-model advantages are real but narrowing - agentic depth, multimodal performance, and the polished tool-use stacks around them. Where the gap actually is in 2026 Benchmarks are imperfect, but the picture they sketch is consistent. On standard reasoning suites - MMLU, GPQA, MATH - open-weight models are within a few percentage points of the closed frontier. On coding - HumanEval, SWE-Bench - the gap is similar. On long-context retrieval, the gap is mostly gone. ...

TL;DR Best entry point: M2 Max 32-64 GB (~£1.4k-£2k) for 7B-13B models at 25-40 tok/s Best sweet spot: M2 Ultra 64-128 GB (~£3k-£4.5k) handles 30B+ models comfortably Best for 70B models: M3 Ultra 128 GB+ (~£5.5k+) with 800+ GB/s bandwidth Newer alternative: M4 Max (£2k-£4k) - lower bandwidth (410-546 GB/s) than Ultra chips, but still solid for 7B-13B models Key rule: Memory bandwidth matters more than raw compute for token generation Reality check: A RTX 5090 rig is 2-3× faster for similar money - buy Mac for simplicity and unified memory You want to run large language models locally on a Mac Studio. Good idea - unified memory is genuinely useful for LLMs. But the specs matter, and there are some hard truths about what “works” versus what feels responsive. More importantly: the right Mac depends entirely on which model you want to run. ...

TL;DR An LLM is the underlying reasoning engine; a chatbot is the product experience wrapped around it - they are related but not the same thing LLMs excel at summarizing, rewriting, generating drafts, and coding, but should be treated as fast collaborators rather than infallible oracles The main model families are frontier models (GPT, Claude, Gemini), open-weight / self-hostable models (Llama), and product-specific assistants (ChatGPT, Cursor, Copilot) Choose the right tool for the job: chatbots for convenience and exploration, APIs for automation, coding-native tools for repo-aware work The market is now split between AI as a consumer product and AI as programmable infrastructure - understanding both layers makes the landscape far less confusing Most people still talk about chatbots and large language models as if they are the same thing. ...