Track Strata configs per model; add UD-Q4_K_XL config

strata/README.md indexes the configs and which one is active; configuration.nix
selects it with strataConfig. UD-Q4_K_XL downloaded and prepared, not active yet.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

README.md

@@ -50,14 +50,14 @@ Current numbers (standard benchmark, idle): prompt ~1,750 tok/s at 4K and ~2,900
 ```
 nixos/        /etc/nixos on llm-nixos (configuration.nix, gpu-unlock.nix, hardware-configuration.nix)
 proxmox/      files from lovey, at their real paths (etc/..., usr/local/bin/..., root/...)
-strata/       strata-iq3_s.json, the engine config (API key removed)
+strata/       one engine config per model/quant (API key removed); README.md says which is active
 pi/           ~/.pi/agent/models.json, settings.json and extensions/ for the client (API key removed)
 docs/         per-layer notes, rebuild steps and the change log
 benchmarks/   live metric snapshots (passive) and later benchmark runs
 ```
 
 **Secrets are not in this repo** (it is public). The Strata API key lives only in
-`/var/lib/strata/api-key` and `strata-iq3_s.json` on the guest; placeholders are marked `<...>`.
+`/var/lib/strata/api-key` and the `strata-*.json` configs on the guest; placeholders are marked `<...>`.
 
 ## Rebuild order
 

docs/changelog.md

@@ -2,6 +2,18 @@
 
 Newest first. Each entry: what broke, the cause, and what fixed it.
 
+## 2026-10-27: UD-Q4_K_XL installed, configs tracked per model
+
+Downloaded Unsloth's UD-Q4_K_XL (111 GB, SHA-256 checked by setup) to test a bigger quant than IQ3_S: Strata's
+own yardstick puts it at 93.1% same-top-token as Q8_0 vs 87.7% for IQ3_S (mean KL 0.056 vs 0.144). Setup's
+check says all 77 GB of its experts fit in the guest's 110 GB. `setup.sh --no-start` wrote
+`strata-unsloth-ud-q4_k_xl.json` beside `strata-iq3_s.json`, which it left byte-identical (compared with
+the backup in `/var/lib/strata/backup-2026-10-27/`).
+
+Configs are now tracked one file per model in [`strata/`](../strata/README.md), which records which is
+active. `nixos/configuration.nix` picks it with `strataConfig`; pi's `models.json` lists both model ids.
+Still serving IQ3_S until the switch.
+
 ## 2026-10-27: power cap 250 W vs 275 W
 
 With the case closed, alternating runs (250/275/250/275, fresh restart each) gave +4.6% prompt speed at

nixos/configuration.nix

@@ -114,10 +114,10 @@
   nix.settings.trusted-users = [ "root" "jason" ];
   systemd.tmpfiles.rules = [ "d /models/strata 0750 strata strata -" ];
 
-  # The API server (setup's run-iq3_s.sh) with offline mode and no downloads. The API key and engine args live in
+  # The API server (setup's run-<model>.sh) with offline mode and no downloads. The API key and engine args live in
-  # strata-iq3_s.json, which setup wrote; host 0.0.0.0, port 8080.
+  # the run config setup wrote; host 0.0.0.0, port 8080. strataConfig picks the active one (repo: strata/README.md).
-  systemd.services.strata = {
+  systemd.services.strata = let strataConfig = "strata-iq3_s.json"; in {
-    description = "Strata inference server (Qwen3.8-Flash-Next IQ3_S)";
+    description = "Strata inference server (${strataConfig})";
     after = [ "network-online.target" "nvidia-persistenced.service" "nvidia-power-limit.service" ];
     wants = [ "network-online.target" ];
     requires = [ "nvidia-persistenced.service" ];
@@ -134,7 +134,7 @@
       User = "strata";
       Group = "strata";
       WorkingDirectory = "/var/lib/strata/Strata";
-      ExecStart = "/var/lib/strata/Strata/.venv/bin/python /var/lib/strata/Strata/serve/server.py --engine strata --config /var/lib/strata/Strata/strata-iq3_s.json --port 8080 --offline";
+      ExecStart = "/var/lib/strata/Strata/.venv/bin/python /var/lib/strata/Strata/serve/server.py --engine strata --config /var/lib/strata/Strata/${strataConfig} --port 8080 --offline";
       Restart = "on-failure";
       RestartSec = 10;
       LimitMEMLOCK = "infinity";  # the expert arena and KV are pinned host memory

pi/models.json

@@ -36,6 +36,23 @@
             "cacheRead": 0,
             "cacheWrite": 0
           }
+        },
+        {
+          "id": "qwen3.8-flash-next-unsloth-ud-q4_k_xl",
+          "name": "Qwen3.8-Flash-Next UD-Q4_K_XL (lovey, Strata)",
+          "reasoning": true,
+          "input": [
+            "text",
+            "image"
+          ],
+          "contextWindow": 131072,
+          "maxTokens": 32768,
+          "cost": {
+            "input": 0,
+            "output": 0,
+            "cacheRead": 0,
+            "cacheWrite": 0
+          }
         }
       ]
     }

strata/README.md

@@ -0,0 +1,30 @@
+# Strata configurations
+
+One file per configuration: the run config `setup.sh` wrote on the guest
+(`/var/lib/strata/Strata/strata-<model>.json`), with the API key replaced by a placeholder. The guest keeps
+every config it has run; the service starts whichever one `strataConfig` names in
+[`nixos/configuration.nix`](../nixos/configuration.nix).
+
+**Active:** `strata-iq3_s.json`
+
+| Config | Model / quant | Experts in RAM | Status | Benchmarks |
+|---|---|---|---|---|
+| [`strata-iq3_s.json`](strata-iq3_s.json) | Qwen3.8-Flash-Next, ISTA-DASLab GSQ-RCO IQ3_S | 47 GB arena + 29 GB PLE table | active since 2026-10-26 | [standard](../benchmarks/standard/README.md), husky-bench `*iq3_s*` |
+| [`strata-unsloth-ud-q4_k_xl.json`](strata-unsloth-ud-q4_k_xl.json) | Qwen3.8-Flash-Next, Unsloth UD-Q4_K_XL (pinned rev `38bb39e`), env `STRATA_HC_Q8=1`, `STRATA_ROUTE_TAIL_SKIP=0` | all 77 GB (setup's estimate) + 29 GB PLE table | installed 2026-10-27, testing | not run yet |
+
+## Switching
+
+1. Set `strataConfig` in `nixos/configuration.nix`, copy it to `/etc/nixos/`, run
+   `sudo nixos-rebuild switch` (restarts `strata`; load takes ~2 min, watch `journalctl -u strata -f`).
+2. Add the config's `model_name` to pi's [`models.json`](../pi/models.json) if it's new; the API serves
+   only the loaded model.
+3. Update **Active** above, the status column, and `docs/changelog.md`.
+
+## Adding a configuration
+
+Run `setup.sh` with `--no-start` (see [docs/strata.md](../docs/strata.md#rebuild)); it writes
+`strata-<model>.json` and `run-<model>.sh` next to the existing ones without touching them. Copy the
+JSON here, replace `api_key` with `<API_KEY: see /var/lib/strata/api-key>`, and add a row.
+
+Name benchmark runs after the config so results stay attributable: husky-bench folders as
+`<model_name>_<power cap>_<effort>`, standard runs with the config in the README table.

strata/strata-unsloth-ud-q4_k_xl.json

@@ -0,0 +1,89 @@
+{
+ "exe": "/var/lib/strata/Strata/engine/strata",
+ "args": [
+  "--pack",
+  "/models/strata/packs/unsloth-ud-q4_k_xl",
+  "--native",
+  "/models/strata/models/unsloth-UD-Q4_K_XL/Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf",
+  "--expert-profile",
+  "/var/lib/strata/Strata/data/expert-profile.bin",
+  "--expert-cache",
+  "auto",
+  "--prefill",
+  "auto",
+  "--spec",
+  "4",
+  "--spec-min-p",
+  "0.5",
+  "--mtp",
+  "/models/strata/mtp/rt",
+  "--max-context",
+  "131072",
+  "--kv",
+  "int8",
+  "--ple-io",
+  "ram",
+  "--kv-resident",
+  "32768",
+  "--vision",
+  "--vram-reserve-mib",
+  "700"
+ ],
+ "cwd": "/var/lib/strata/Strata",
+ "tokenizer": "/models/strata/packs/unsloth-ud-q4_k_xl/tokenizer",
+ "model_name": "qwen3.8-flash-next-unsloth-ud-q4_k_xl",
+ "log": "/var/lib/strata/Strata/strata-unsloth-ud-q4_k_xl.log",
+ "lib_dirs": [
+  "/nix/store/7mi3cxyj9rgx76yxr6jg4z8i3cvb3dmz-cuda-merged-13.0/bin"
+ ],
+ "port": 8080,
+ "env": {
+  "STRATA_HC_Q8": "1",
+  "STRATA_ROUTE_TAIL_SKIP": "0"
+ },
+ "gpu": [
+  0,
+  1
+ ],
+ "gpus_asked": true,
+ "layer_split": "auto",
+ "host": "0.0.0.0",
+ "api_key": "<API_KEY: see /var/lib/strata/api-key>",
+ "open_browser": false,
+ "vision": {
+  "exe": "/var/lib/strata/Strata/engine/strata-vision",
+  "mmproj": "/models/strata/models/mmproj-Qwen3.8-Flash-Next-BF16.gguf",
+  "model": "/models/strata/models/unsloth-UD-Q4_K_XL/Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf",
+  "gpu": true,
+  "max_tokens": 1024
+ },
+ "args_written": [
+  "--pack",
+  "/models/strata/packs/unsloth-ud-q4_k_xl",
+  "--native",
+  "/models/strata/models/unsloth-UD-Q4_K_XL/Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf",
+  "--expert-profile",
+  "/var/lib/strata/Strata/data/expert-profile.bin",
+  "--expert-cache",
+  "auto",
+  "--prefill",
+  "auto",
+  "--spec",
+  "4",
+  "--spec-min-p",
+  "0.5",
+  "--mtp",
+  "/models/strata/mtp/rt",
+  "--max-context",
+  "131072",
+  "--kv",
+  "int8",
+  "--ple-io",
+  "ram",
+  "--kv-resident",
+  "32768",
+  "--vision",
+  "--vram-reserve-mib",
+  "700"
+ ]
+}