Skip to main content

Blog

Articles, guides, and insights on local artificial intelligence

7 articles found per "MoE"

Mistral Large 4 in open weights: a 1T MoE (52B active) for on-premise inference
ModelsIntermediate

Mistral Large 4 in open weights: a 1T MoE (52B active) for on-premise inference

Mistral released Large 4 in open weights (1.03T total, 52B active, 1M context, open-weight license): an article teaching how to read MoE specs and do the RAM, quantization and speed math for on-premise inference.

iaLocale Team
November 14, 2026
Nemotron 3.5 Bolt: NVIDIA's 74B MoE with ~9B active — what changes on your desktop
ModelsIntermediate

Nemotron 3.5 Bolt: NVIDIA's 74B MoE with ~9B active — what changes on your desktop

74B parameters, 9B active: NVIDIA's MoE for local agents fits 24GB of VRAM via IQ2 quantization. Real VRAM, declared benchmarks and honest limits.

iaLocale Team
November 2, 2026
MiniCPM-V 4.7: the 35B MoE that runs on a smartphone with 3 GB of RAM
ModelsIntermediate

MiniCPM-V 4.7: the 35B MoE that runs on a smartphone with 3 GB of RAM

MiniCPM-V 4.7 (35B total, ~3B active, released October 12, 2026 by OpenBMB and ModelBest) is the first open MoE in the series, vision-language: multiple images, video, OCR. 13+ tok/s with 3 GB of RAM on an iPhone 17 Pro Max, 17+ on Android. Official quantizations BF16, FP8, INT4, AWQ, GPTQ, GGUF; engines Ollama, llama.cpp, vLLM, SGLang. The three techniques: Lookahead Expert Scheduling, fine per-level quantization, DSpark speculative sampling.

iaLocale Team
October 21, 2026
Ling 3.1 Flash: 560B open-weight with MIT license and 1M context — what changes if you have 24GB of VRAM
ModelsIntermediate

Ling 3.1 Flash: 560B open-weight with MIT license and 1M context — what changes if you have 24GB of VRAM

inclusionAI's Ling 3.1 Flash: hybrid MoE 560B total / 25B active, native 1M-token context, FP8 checkpoint, MIT license. What it concretely means for 24GB of VRAM: quantizations, parallelism and API costs.

iaLocale Team
October 19, 2026
Aleph Alpha's Kolibri: the 78B MoE that runs (almost) locally
ModelsIntermediate

Aleph Alpha's Kolibri: the 78B MoE that runs (almost) locally

Aleph Alpha's Kolibri (78.1B/3.46B, Apache 2.0, FP8) is the European open-weight MoE: reasoning, tool calling and context up to 1M tokens. In FP8 it weighs ~78GB of VRAM: it runs on an RTX 5090 32GB + shared RAM or on unified-memory Macs; for practical adoption the kolibri1 architecture in llama.cpp and Ollama/LM Studio builds are still missing.

iaLocale Team
October 18, 2026
gpt-oss: OpenAI's open reasoning model
ModelsIntermediate

gpt-oss: OpenAI's open reasoning model

21B total parameters but only 3.6B active, native MXFP4 weights and 128K of context: OpenAI's first open reasoning model fits in 16GB. What that means in practice.

iaLocale Team
October 11, 2026
How to Read a Model's Spec Sheet: Family, Size, Context
ModelsIntermediate

How to Read a Model's Spec Sheet: Family, Size, Context

A guide to reading a model's specs: family, total and active size, context window, quantization, benchmarks and license, with a worked example on DeepSeek V4.1 Flash.

iaLocale Team
September 26, 2026