Skip to content

ADR-0003 — Apex Model Choices (Phase 1)

Why qwen3.5:122b-a10b for production, GLM-4.6V Flash 9B + Qwen 3.6 27B for experimental.

Status: Active — deployed 2026-05-19.

Initial Apex model deployment:

TierAliasBacking modelWhereQ4 size
Productionapex-coreqwen3.5:122b-a10bSentinel (Mac Studio)81 GB
Experimentallab-flashhaervwe/GLM-4.6V-Flash-9BRyzen6 GB
Experimentallab-generalhuihui_ai/Qwen3.6-abliterated:27bRyzen17 GB

We need locally-served LLMs that:

  • Match Claude’s capability stack (vision, tools, coding, thinking) on production tier
  • Fit our hardware (Mac Studio 128 GB unified, Ryzen 32 GB + 8 GB GPU)
  • Have permissive licenses (no enterprise restrictions)
  • Run on Ollama (existing infra)
  • Unified vision-language model (no separate VL variant) — handles image input natively
  • MoE architecture (10B active per token / 125B total) — production throughput on M1 Ultra
  • 262K context window
  • Strong on MMMU, MathVision, coding benchmarks
  • Q4_K_M ≈ 81 GB — fits Sentinel’s 128 GB with ~30-40 GB headroom for KV cache and OS
  • Closest open-weight equivalent to Claude Sonnet/Opus for our use cases
  • Native vision + tool calling — most advanced multimodal function calling we’ve seen at small size
  • 6 GB fits Ryzen’s 8 GB GPU entirely — 50+ tok/s expected
  • 128K context
  • “Flash” variant of Z.AI’s GLM family — known for SWE-bench coding strength
  • Reserved for: fast classification, vision-driven workflows, doc tooling automation

lab-general: Qwen 3.6 27B (huihui_ai/Qwen3.6-abliterated)

Section titled “lab-general: Qwen 3.6 27B (huihui_ai/Qwen3.6-abliterated)”
  • Experimental variant for internal workflows requiring flexible output policies
  • 17 GB Q4_K_M — partial GPU offload on Ryzen (~10-15 tok/s)
  • 256K context, tool calling, thinking mode
  • Reserved for internal automation. Not client-facing.
AlternativeRejected because
DeepSeek V4-Pro local800 GB+, datacenter-only. Stays as cortex-* cloud passthrough.
Kimi K2.6 local1T-A32B, ~500 GB at native INT4. Datacenter-only.
Llama 4 Scout local109B-A17B, ~60 GB but no good abliterated variants yet; less mature on Ollama
Qwen 2.5 VL 72BOlder generation, Qwen 3.5 unified VLM strictly better
InternVL3 78BVision-only specialist; we need general reasoning + vision
Pixtral 12BSmaller capability ceiling for production tier

DeepSeek V4 and Kimi K2.6 are kept available as cloud passthroughs (cortex-* aliases) for when 1M+ context or top-tier reasoning is needed.

Established as part of this decision:

  • apex-* — production, client-facing, premium quality (Sentinel)
  • lab-* — internal, experimental (Ryzen)
  • cortex-* — cloud passthroughs (reserved namespace)

Apps reference aliases, not backing model names. Backing models can change without touching CMMD/Forge code.

  • Hardware capacity well-utilized: Sentinel runs flagship, Ryzen runs two complementary smaller models
  • Same model family (Qwen) on production + experimental — prompt patterns transfer
  • Vision is universally available across all three aliases
  • Mac Studio cleanup (Spotlight off, Apple Intelligence off) was required to free 80+ GB for apex-core to fit; ongoing operational discipline needed to keep that headroom

New aliases go through:

  1. PR to cmmd-center/apex/models/registry.yml
  2. Phase D drift workflow drafts doc updates to this page automatically
  3. Human reviews and merges