A collection of 36 posts
MiniMax M3.1 Flash went GA on 19 Oct 2026 at a flat $0.15/$0.60 per 1M tokens, half of M3's price. A 428B/23B MoE with 1M context and always-on reasoning, it scores 43 on Artificial Analysis vs M3's 29. Covers license terms, vLLM/SGLang serving and M Plan tiers.
Meta's 816B/42B-active open-weight MoE (Oct 15, 2026): what the Muse Model License allows, hardware from two Mac Studios to 2TB GPU clusters, how to run it with llama.cpp or vLLM, OpenRouter pricing (Oct 2026) and model-card benchmarks.
Z.ai added GLM-5.3 Prime and GLM-5.3 FlashX in September 2026. Neither is a new model — both are accelerated serving tiers of weights that already shipped. Here is the full GLM-5.3-era lineup, with verified prices, licences and a decision rule.
MiMo-V2.6-Flash is Xiaomi's MIT-licensed 309B/15B-active MoE at $0.14/$0.28 per 1M tokens. The Distill-Qwen-9B runs on an 8 GB GPU. Specs, benchmarks, VRAM by quant, and Ollama / LM Studio / llama.cpp commands.
DeepSeek-V4.1-Flash-1017 (17 Oct 2026): same deepseek-flash ID and $0.30/$1.20 peak pricing, Terminal-Bench 4.0 up from 31.2 to 42.3, AA index 45 (was 39), 16% fewer output tokens. Plus Search & Fetch at $0.75/1K, the Oct 15 outage credits, V4-Pro status and Unsloth GGUFs.
Every Qwen 3.8 variant in one table: 27B, Flash-Next, 2.4T-A95B and Max, with params, context, licence and price, plus a single rule for picking one.
Alibaba's cheap multimodal tier: $0.15/$0.47 per 1M tokens, 1M context, and open weights under the Qwen Community License. Specs, benchmarks and how it compares to GLM-5.3-Flash and DeepSeek V4-Flash.
GLM-5.3-Flash is 320B-A18B, multimodal and roughly 9x cheaper than GLM-5.2's 744B-A40B. A verified head-to-head on specs, benchmarks, cost and self-hosting — plus the cases where GLM-5.2 still wins.
GLM-5.3-Flash ships 320B parameters in a 328 GB native-FP8 checkpoint, so the 18B active count tells you nothing about the memory you need. Here are the real hardware requirements by quantisation, plus working vLLM, SGLang, llama.cpp and Apple Silicon setups.
Z.ai's GLM-5.3-Flash is the model that ran anonymously as Ox Alpha: a 320B-total, 18B-active natively multimodal MoE with a 1M-token context and MIT open weights. Here are the verified specs, pricing and benchmarks.
Ox Alpha was Z.ai's GLM-5.3-Flash, confirmed on 26 August 2026. The free stealth preview has ended and the OpenRouter listing is gone. Verified specs, MIT-licensed weights, real pricing, and how to use the model now.
The 17GB Apache-2.0 model scoring 52 on Artificial Analysis: which benchmark numbers to trust, the overthinking fix, VRAM needs, and how it compares to Claude and the 2.4T flagship.
The config.json diff between Qwen 3.8-27B and Qwen 3.6-27B is empty — same layers, same hidden size, same vocab. Every gain came from post-training. Here's what actually changed, what the upgrade costs you, and who should stay on 3.6.
A practical, honest guide to running MiniMax M3 (428B MoE) locally: VRAM/RAM math, quant options, and the Ollama, vLLM, and LM Studio paths.
DiffusionGemma 26B-A4B is Google’s first open-weight text-diffusion LLM — a 25.2B MoE built on Gemma 4 that generates text in parallel for up to 4x faster output.
Cohere North Mini Code 1.0 is an open-weight 30B MoE coding model (3B active, 256K context, Apache 2.0) built for agentic software engineering. Specs, benchmarks, access.
Qwen3.7-Max is the closed flagship with higher vendor benchmarks and a 1M context; Kimi K2.7 Code is the open-weights, cheaper agentic specialist. We compare access, benchmarks, pricing, local feasibility, and which to use for autonomous coding.
Ornith 1.0 is a free, MIT-licensed, self-hostable coding model. Opus 4.8 is the closed frontier flagship. A benchmark-grounded, harness-honest comparison of where each wins on agentic coding in 2026.
DeepSeek V4 and Qwen 3.7 post near-identical coding benchmarks, but only one is actually open. A specifics-first comparison of architecture, local-run feasibility, API pricing, and license for developers choosing a coding model in 2026.
A realistic, no-hype guide to running Qwen 3.6 27B locally as a Claude Code alternative: benchmarks vs Opus, the hardware and quant you actually need, how to wire it in, where it holds up, and what a hybrid setup actually saves you.
Two new MIT open-weights coding models shipped a day apart in June 2026. We compare architecture, coding benchmarks, local hardware, and API pricing for Ornith 1.0 vs GLM 5.2 — with an honest, no-hype verdict on which to pick.
Zhipu Z.ai shipped GLM 5.2 today on every GLM Coding Plan tier with a usable 1M-token context window. Standalone API, the Z.ai chatbot, and the MIT open weights are arriving next week. No benchmarks yet — here's what's confirmed, what's not, and how it fits next to GLM-5.1.
JetBrains released Mellum2, a 12B Mixture-of-Experts model that activates just 2.5B parameters per token and ships under Apache 2.0. Here's what it is, where it fits in an AI stack, and how to put it to work.
A practical, size-tier-by-tier comparison of Google's Gemma 4 and Alibaba's Qwen 3.5 — benchmarks, coding, reasoning, multilingual, and how to run each locally in 2026.
Qwen 3.7 weights are not on Hugging Face yet (May 20, 2026). Here are the honest ways to use it today, and exactly what to run locally instead.