English
← Back to Home

Model architecture

Structures that determine how models represent and transform information.

3 entries

Frameworks and representation

Software and data interfaces used to build, train, and run models.

3 entries

Training and post-training

Scaling, adaptation, and preference methods that shape model capabilities and behavior.

4 entries

Inference and deployment

Memory, scheduling, compression, and runtime techniques used to serve models.

5 entries

APPLICATION LAYER

Application architecture

Models become products through workflows, tools, context exchange, guardrails, and evaluation. The existing MCP and Tools sections cover this application layer without duplicating it here.

Open-model cases

Model families examined through code, weights, training disclosure, and license.

9 entries
2023

Llama

Meta’s downloadable-weight model family helped expand local inference and downstream fine-tuning. Its releases use Llama-specific terms, so "open weights" is more precise than assuming OSI-defined open source.

  • open weights
  • community license
  • model family
2023

Qwen

Alibaba’s Qwen family spans dense, expert-routed, multilingual, and multimodal releases. Many checkpoints are openly downloadable, but license and disclosure claims should be checked at the individual model-card level.

  • multilingual
  • dense and MoE
  • open weights
2023

Mistral / Mixtral

Mistral AI’s family includes both dense Mistral models and expert-routed Mixtral models. Some releases use permissive licenses while others do not, so openness must be assessed per artifact.

  • dense models
  • MoE
  • open weights
2023

DeepSeek

DeepSeek’s downloadable releases made MoE design, reasoning post-training, and efficient serving widely studied. Code and weights may use different licenses, and training-data disclosure is a separate dimension.

  • MoE
  • reasoning
  • open weights
2024

Gemma

Google’s downloadable-weight family connects Gemini-derived research with local, edge, and hosted deployment. Google calls the family open models, while usage remains governed by Gemma-specific terms.

  • open weights
  • lightweight models
  • edge deployment
2024

OLMo

Ai2 releases the OLMo family with its pretraining data, training code, intermediate checkpoints and logs alongside the weights. The first OLMo appeared in February 2024, OLMo 2 that November, and Olmo 3 in November 2025 with 7B and 32B Base, Instruct and Think variants under Apache 2.0. It is the case where all four things worth checking separately — code, weights, training disclosure and license — are actually published, which makes it a reference point against families that release weights alone.

  • fully open
  • open training data
  • intermediate checkpoints
2025

gpt-oss

OpenAI’s gpt-oss-120b and 20b are downloadable MoE reasoning models designed for local and hosted inference. Their Apache 2.0 weights and reference implementations broaden deployment access, while the pretraining dataset itself is not released.

  • open weights
  • reasoning
  • MoE
2026

GLM-5

Z.ai’s GLM-5 series is a large MoE language-model family for reasoning, coding, and long-horizon agentic work. GLM-5 appeared in February 2026, 5.1 in April, 5.2 in June at 753 billion parameters with a one-million-token context window, and 5.3 in August on the same base with post-training changes; the smaller GLM-5.3-Flash followed days later at 320 billion total and 18 billion active parameters. The larger members’ scale makes self-hosting resource-intensive.

  • open weights
  • MoE
  • long context
2026

Kimi K3

Moonshot AI released Kimi K3 in July 2026 as an open-weight, native-multimodal MoE language model with 2.8 trillion total parameters, 104 billion active parameters, and a one-million-token context window. It targets long-horizon coding, knowledge work, and tool-using agents, while its scale makes local deployment demanding.

  • open weights
  • MoE
  • long context

This is a curated technical map, not a claim of comprehensive coverage.