[Update] bulk update

fl/.config/llamacpp/README.md

@@ -4,7 +4,8 @@ llama.cpp in **router mode** serving ~10 model presets from one 16 GB GPU.
 Last full tune: **2026-07-16** (decode numbers measured then via `bench.py`, unless a preset comment in `config.ini` says otherwise).
 Last full clean sweep: **2026-08-08 03:22** — all 11 presets loaded and ran green (baseline 2.0 GB) after the week's coder-race/KV-fix/gemma-sidecar round.
 
-- **Box**: AMD RX 7600 XT 16 GB (ROCm, ~288 GB/s) + Ryzen 5600X (6 cores) + 48 GB RAM.
+- **Box**: AMD RX 7600 XT 16 GB (~288 GB/s; backend = Arch `llama.cpp-vulkan` / RADV, **not** ROCm —
+  `rocm-smi` is only the VRAM monitor) + Ryzen 5600X (6 cores) + 48 GB RAM.
   ⚠ The GPU **also drives the display** — see [VRAM safety](#vram-safety-the-golden-rules).
 - **Endpoints**: LAN `http://$SERVER:11343/v1` · remote `https://<own-domain>/api/v1`
   (own reverse proxy to the same server; requires an API key. Only the LAN endpoint is keyless).
@@ -36,7 +37,7 @@ After ANY preset change: restart + `./bench.py -m <changed-ids>` and check the g
 
 ## VRAM safety (the golden rules)
 
-ROCm does not OOM cleanly — an overcommitted model spills into GTT (system RAM),
+The amdgpu driver does not OOM cleanly — an overcommitted model spills into GTT (system RAM),
 starves the desktop and freezes the PC (reboot). Hard-won rules:
 
 1. Keep every preset's benched **VRAM free ≥ 2.5 GB** (idle desktop uses ~1.3 of 17.2).
@@ -60,6 +61,7 @@ starves the desktop and freezes the PC (reboot). Hard-won rules:
 | `Qwen3-Coder-30B-Instruct-UD-Q3_K_XL` | **~30** clean / 27.0 evening @moe12 | 32k | — | **main agent coder** — won the 2026-08-06 quant race; moe12 verified evening 08-07 + clean 08-08 |
 | `GLM-4.7-Flash-UD-Q4_K_XL` | **21.5** @moe22 | 24k | reasoning | quality coder (opencode subagents); KV fix + moe22 ✓ verified clean 08-08 |
 | `Qwen3-Coder-Next-UD-IQ3_XXS` | 16.0 | **128k** | 80B-A3B | long-session coder (128k ctx) |
+| `Qwen3.8-27B-UD-IQ3_XXS` | 14.5 (10.9 w/o MTP) | 24k | vision, MTP, hybrid reasoner | ⚠ **clean-desktop specialty** (kept 09-10 over the ≥22 gate) — dense-27B quality, slow: its Gated-DeltaNet layers are Vulkan-bound (prefill ~30). 2.5 GB free @1.6 baseline @24k (✓ 09-10); **never on a busy evening desktop** (~1 GB free = GTT freeze) |
 | `Qwen3-Embedding-0.6B` | 33 (CPU) | 8k | CPU-only, `/v1/embeddings` | RAG/search embedder (not a chat model) |
 
 Expected run-to-run spread: MTP models swing ±15% with draft **acceptance rate** (content-
@@ -77,6 +79,9 @@ Treat clean night runs as the reference; don't retune on daytime deltas.
 - **Hard reasoning**: `35B-Thinking` (quality) or `gpt-oss-20b` (speed + tool use).
   Their multi-second TTFT is the reasoning phase streaming first — not a slow load.
   For quick interactive gpt-oss answers use `gpt-oss-20b-low` (reasoning effort low).
+- **Best single-model quality, speed no object** (quiet desktop only): `Qwen3.8-27B` — dense
+  27B hybrid reasoner + vision at ~14.5 t/s; it cannot go faster on this card (GDN layers on
+  Vulkan), and a busy evening desktop pushes it into GTT-freeze territory — check `rocm-smi` first.
 - **Images**: `gemma-4-26B` for quality, `gemma-4-E4B` or `Qwen3.5-9B` for speed,
   `Qwen3.6-35B` when you want the daily driver to see the screenshot.
 - **Long one-shot documents**: `gemma-4-E4B` — 185 t/s prefill eats 64k in ~6 min
@@ -123,6 +128,9 @@ The embedder is deliberately absent from chat clients.
 2026-08-06: the coder id changed `…-IQ4_XS` → `…-UD-Q3_K_XL` in all six client files
 (common + lw overlays) after the quant race; OWUI picks the new id up automatically from
 the router, but chats/presets saved against the old id need re-picking.
+2026-08-16: `Qwen3.8-27B-UD-IQ3_XXS` (⚗ candidate) added to all six client files.
+2026-09-10: kept as ⚠ clean-desktop specialty after the gate bench finally ran on the v3 gguf
+(14.5 t/s MTP / 10.9 base, 2.8 GB free @1.5); server ctx restored to 24576 = client ctx, no client edits.
 
 ## Tuning cheat-sheet
 
@@ -135,7 +143,10 @@ the router, but chats/presets saved against the old id need re-picking.
   4-bit now; 3-bit was only ~2 t/s faster). Coders want ≥4-bit; chat tolerates UD 3-bit.
 - **MTP / spec decode** (`spec-type draft-mtp`): ~1.5–2× decode. Qwen3.5/3.6 embed the
   head in the *MTP-repo* GGUF (same filename as plain repo — size is the tell);
-  gemma-4 uses a separate `mtp-*.gguf` draft file. **No MTP possible yet for**:
+  gemma-4 uses a separate `mtp-*.gguf` draft file; Qwen3.8 ships the head in the
+  *main*-repo GGUFs for ≥ Q2_K_XL (≤ IQ2_S are stripped — use the repo's `MTP/mtp-*.gguf`
+  draft instead). On the hybrid 27B it is only +33% (10.9→14.5) and costs 1.5 GB: every
+  speculative step re-runs the Gated-DeltaNet layers. **No MTP possible yet for**:
   GLM-4.7-Flash (conversion drops the head — expected ~1.5× when llama.cpp lands it),
   Qwen3-Coder-Next (Qwen3-Next head exists upstream, no GGUF ships it), gpt-oss and
   Qwen3-Coder-30B (no head exists). Recheck releases occasionally.