diff --git a/docs/03-SERVICES-OTHER.md b/docs/03-SERVICES-OTHER.md
index 3dc0263..40e2f5e 100644
--- a/docs/03-SERVICES-OTHER.md
+++ b/docs/03-SERVICES-OTHER.md
@@ -510,13 +510,13 @@ Non-critical services that enhance functionality but don't affect core network o
 |---------|-------|
 | `HSA_OVERRIDE_GFX_VERSION` | 11.0.0 (report 780M as gfx1100) |
 | `OLLAMA_IGPU_ENABLE` | 1 (Ollama 0.30+ drops iGPUs otherwise) |
-| `OLLAMA_FLASH_ATTENTION` | 1 |
-| `OLLAMA_KV_CACHE_TYPE` | q8_0 |
 | devices | `/dev/kfd`, `/dev/dri` |
 | group_add | `18` (video) |
 
 **Verified:** Ornith 1.0 9B GGUF runs 100% on GPU (33/33 layers), ~11 tok/s. iGPU is RAM-bandwidth bound (shared GTT, ~23 GiB addressable). 9B fits; 35B RAM-tight (no swap); 397B not feasible.
 
+**⚠️ Limitation:** large prompts (~10k+ tokens) crash the iGPU (`ROCm unspecified launch failure` — gfx1103 rocBLAS). Tried flash-attn off, gfx1100/gfx1102, `num_batch=128` — all crash, so `OLLAMA_FLASH_ATTENTION`/`OLLAMA_KV_CACHE_TYPE=q8_0` were removed. Good for direct/interactive chat only, **not** an agent backend with big system prompts (tried as Hermes' model with a ~15.5k-token prompt — crashed every call, reverted to cloud).
+
 ---
 
 ## Stopped/Disabled Services