homepage+docs: frank-archon runs our own GPTQ-w4 build, link our HF publication

2026-10-08 22:15:33 -07:00
parent 958b10545e
commit 184a5c665a
3 changed files with 11 additions and 4 deletions
@@ -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"