From 184a5c665a70c8abb02b36a08a3a4629c7d49b5c Mon Sep 17 00:00:00 2001 From: Frank Date: Thu, 8 Oct 2026 22:15:33 -0700 Subject: [PATCH] homepage+docs: frank-archon runs our own GPTQ-w4 build, link our HF publication --- serverAppConfigs-docs/Infrastructure/Homepage.md | 7 +++++++ shared/homepage/docs.html | 4 ++-- shared/homepage/services.json | 4 ++-- 3 files changed, 11 insertions(+), 4 deletions(-) diff --git a/serverAppConfigs-docs/Infrastructure/Homepage.md b/serverAppConfigs-docs/Infrastructure/Homepage.md index c87fe75..5b54ba6 100644 --- a/serverAppConfigs-docs/Infrastructure/Homepage.md +++ b/serverAppConfigs-docs/Infrastructure/Homepage.md @@ -226,6 +226,13 @@ its Pi-hole specifics — family members off the LAN cannot use house-DNS advice; the bullet now just says the names resolve on the home network. +**Archon card runs the fleet's own model (2026-10-08):** the +`frank-archon` homepage card and docs Model bullet now say the payload +is our in-house GPTQ-w4 quant of Swift1.5-Qwen3.8-Flash-Next and link +our HF publication (`frank8465/Swift-1.5-Qwen3.8-Flash-Next-GPTQ-W4A8-Radiance-AMD-R9700`) +in place of the FP8-era base-model link; capacity line says three +submissions (`--max-num-seqs 3`). + ## Design decision — 2026-08-22 The live up/down check runs server-side. A checker on Dankclaw probes each backend and writes a same-origin `status.json`. The page fetches only that file and renders the badges. The browser never calls a backend directly. The checker runs as a systemd timer every 3 minutes. diff --git a/shared/homepage/docs.html b/shared/homepage/docs.html index a86a993..5b9f28f 100644 --- a/shared/homepage/docs.html +++ b/shared/homepage/docs.html @@ -113,9 +113,9 @@

frank-archon — the big one (api id: frank-primary)

diff --git a/shared/homepage/services.json b/shared/homepage/services.json index fd5b57b..49d12c9 100644 --- a/shared/homepage/services.json +++ b/shared/homepage/services.json @@ -366,13 +366,13 @@ "model": { "unit": "archon", "role": "Frank's strongest and fastest model runtime", - "hf": "https://huggingface.co/Qwen/Qwen3.8-Flash-Next-FP8", + "hf": "https://huggingface.co/frank8465/Swift-1.5-Qwen3.8-Flash-Next-GPTQ-W4A8-Radiance-AMD-R9700", "tagline": "...Power Overwhelming...", "sfx": [ "archon-power.ogg" ], "equiv": "Equivalent to Claude Opus 4.8 / OpenAI-Terra (Summer 2026 frontier intelligence).", - "spec": "Qwen3.8-Flash-Next at native FP8 precision (radiance, 173 GiB) on twin AMD R9700s with more than 200 GB of system RAM — 200k-token context, two submissions at a time; sees images.", + "spec": "Our own build: a GPTQ-w4 quant of Swift1.5-Qwen3.8-Flash-Next, quantized and tuned in-house (radiance, ~114 GiB) on twin AMD R9700s with more than 200 GB of system RAM — 200k-token context, three submissions at a time; sees images.", "inputs": [ "text", "image"