docs: reframe stale qwen36-stamped narrative as legacy / recovery

Five doc surfaces still carried the v0.6.0-era "bundle is
qwen36-stamped, fails today, rebadge first" framing that the earlier
83022eb / 4811e8d collapses missed: the README "What's here" intro
paragraph + load_bundle.sh / heal_hf_pull.sh table cells, the "Local
apps" intro + Ollama cell, the load_bundle.sh and heal_hf_pull.sh
preambles, and the Makefile load-bundle help text. Reframed each to
describe the current qwen35-stamped reality; the qwen36 rebadge code
paths stay, but their docs now say "legacy v0.6.0 recovery, no-op on
fresh pulls". Net -15 lines.

Upstream re-poll (gh search ggml-org/llama.cpp + ollama/ollama for
qwen36, 2026-05-19): still no arch entry, still no open PR or issue
— same answer as the earlier recheck; the qwen35 stamp stands.

CHANGELOG [Unreleased] picks up a "Changed (round-trip residue
cleanup)" bullet with the per-surface breakdown.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

CHANGELOG.md

@@ -61,6 +61,46 @@ and documentation**, not the underlying base model.
   (skips early); load-bundle does a no-op rebadge on a qwen35 bundle
   and runs `ollama create` as normal.
 
+### Changed (round-trip residue cleanup)
+- Five doc surfaces still carried the v0.6.0-era "bundle is
+  qwen36-stamped, fails today, rebadge to qwen35 first" narrative
+  that the earlier `83022eb` / `4811e8d` collapses missed. Reframed
+  to describe the current qwen35-stamped reality:
+  - **README** "What's here" intro paragraph (the secondary
+    TL;DR-style block above Architecture): flipped the
+    "qwen36-stamped → fails today, see Heads-up above" example to
+    the same one-liner the primary TL;DR uses; dropped the "as a
+    working-today fallback while the bundle waits on upstream
+    qwen36 support" framing from the Q3_K_S paragraph since
+    there's no longer anything to wait on.
+  - **README** "Local apps" intro paragraph: removed the entire
+    "every row below assumes you've rebadged it to qwen35"
+    caveat; trimmed "or to bypass the qwen36 block today" from
+    the Ollama table cell.
+  - **README** "What's here" table cells for `load_bundle.sh`
+    and `heal_hf_pull.sh`: reframed each as primary qwen35 path
+    + legacy qwen36 recovery branch, instead of describing the
+    rebadge as mandatory.
+  - **`scripts/load_bundle.sh`** preamble: rewritten to describe
+    the current qwen35-stamped bundle as the default; the qwen36
+    rebadge branch is documented as a fallback for legacy
+    pre-`964e418` checkouts.
+  - **`scripts/heal_hf_pull.sh`** preamble: reframed as recovery
+    for pre-`964e418` v0.6.0-era pulls; clarified that fresh
+    pulls don't need it.
+  - **Makefile** `load-bundle` help text + example comment: dropped
+    the "qwen36-stamped bundle, rebadged to qwen35" framing.
+  Net -15 lines. Upstream re-poll (`gh search` against
+  `ggml-org/llama.cpp` + `ollama/ollama` for `qwen36` PRs/issues,
+  2026-05-19): no qwen36 arch entry, no open PR or tracking issue
+  — same answer as the earlier subagent recheck; the
+  `qwen35` stamp choice still stands. (Side-finding worth noting
+  for a future README update: llama.cpp PR `#22673` merged
+  2026-05-16 adds MTP speculative decoding for Qwen3.6, so the
+  Architecture section's "MTP head trained for speculative
+  decoding" claim now has a usable consumer path — out of scope
+  for this cleanup.)
+
 ### Added
 - `scripts/check.sh` now greps for the `VAR="$(cmd 2>/dev/null | filter)"`
   silent-exit pattern that bit `heal_hf_pull.sh` (commit 385ed94).

Makefile

@@ -13,7 +13,7 @@
 #   make build                          # Q4_K_M from unsloth (qwen35-stamped, loads today)
 #   make build QUANT=Q3_K_S             # smaller quant
 #   make build GGUF_PATH=~/models/Qwen3.6-27B-Q4_K_M.gguf
-#   make load-bundle                    # this repo's qwen36-stamped bundle, rebadged to qwen35 + loaded
+#   make load-bundle                    # this repo's bundled GGUF -> local Ollama tag (smudge LFS if needed)
 #   make smoke
 #   make check
 #   make clean
@@ -40,7 +40,7 @@ endif
 build:  ## Download qwen35-stamped GGUF from unsloth and run 'ollama create' (loads today).
 	GGUF_PATH=$(GGUF_PATH) TAG=$(TAG) ./scripts/build.sh $(QUANT)
 
-load-bundle:  ## Load THIS repo's qwen36-stamped bundle (smudge LFS + rebadge to qwen35 + ollama create).
+load-bundle:  ## Load THIS repo's bundled GGUF into a local Ollama tag (smudge LFS + ollama create).
 	TAG=$(TAG) ./scripts/load_bundle.sh
 
 heal-hf:  ## Heal an already-pulled hf.co/FoolDev/Thanatos-27B tag in-store (rebadge blob + manifest digest).

README.md

@@ -122,8 +122,8 @@ The 27B is **dense**: every parameter participates in every forward pass. It's s
 | `template`, `system`, `params` | Used by HF's Ollama bridge when users `ollama run hf.co/FoolDev/Thanatos-27B` directly (the bridge does **not** read `Modelfile` — see [HF Ollama docs](https://huggingface.co/docs/hub/en/ollama)). Mirrors the `Modelfile`'s template / system prompt / sampling params. |
 | `examples/` | Ready-to-run Python clients for Ollama, Transformers, and llama-cpp-python |
 | `scripts/build.sh` | Pulls a qwen35-stamped GGUF from `unsloth/Qwen3.6-27B-GGUF` and runs `ollama create` (loads on today's llama.cpp / Ollama; see `make build`) |
-| `scripts/load_bundle.sh` | One-shot path from *this repo's* qwen36-stamped bundle → loadable Ollama tag (smudges LFS pointer via `hf download` if needed, rebadges qwen36 → qwen35, runs `ollama create`; see `make load-bundle`) |
-| `scripts/heal_hf_pull.sh` | Heal an already-pulled `hf.co/FoolDev/Thanatos-27B:...` tag in-store: rebadges its model blob qwen36 → qwen35 and rewrites the manifest's model-layer digest so the same tag becomes loadable in place. Use after `ollama run hf.co/FoolDev/Thanatos-27B` has failed once and left ~17 GB in the blob store; see `make heal-hf`. Idempotent — tags already on qwen35 are skipped. |
+| `scripts/load_bundle.sh` | One-shot path from *this repo's* bundle → loadable local Ollama tag (smudges LFS pointer via `hf download` if needed, runs `ollama create`; see `make load-bundle`). Carries a qwen36 → qwen35 rebadge branch for legacy v0.6.0-era checkouts — no-op on the current qwen35-stamped bundle. |
+| `scripts/heal_hf_pull.sh` | Recovery for users who pulled `hf.co/FoolDev/Thanatos-27B` *before* the qwen35 re-stamp (commits `964e418` / `72259c1`) and still have the qwen36-stamped blob in their local Ollama store: rebadges the blob qwen36 → qwen35 and rewrites the manifest's model-layer digest so the same tag becomes loadable in place. See `make heal-hf`. Idempotent and a no-op on tags already on qwen35 — fresh pulls don't need it. |
 | `scripts/smoke_test.sh` | Verifies an Ollama daemon + model, runs a round-trip, asserts no chat-template tokens leak into the response. With `TOOLS_TEST=1`, also exercises an end-to-end tool-call round-trip and checks the response shape |
 | `scripts/bench.sh` | Measures real tok/s using Ollama's `eval_count` / `eval_duration` metadata over a 3-prompt mix (run `make bench`) |
 | `scripts/fetch_vision.sh` | Pulls the vision projector (`mmproj-F16.gguf`) for llama.cpp (Ollama vision is broken upstream — see [Vision](#vision)). Renamed from `fetch_mmproj.sh` because HF's Ollama bridge auto-indexed the script as a vision projector layer (filename pattern match). |
@@ -136,17 +136,15 @@ The 27B is **dense**: every parameter participates in every forward pass. It's s
 | `README.md` | This file |
 
 This repo ships a single GGUF to back the HF/Ollama "Use this model"
-widget — `Thanatos-27B.Q4_K_M.gguf` (~17 GB, qwen36-stamped):
+widget — `Thanatos-27B.Q4_K_M.gguf` (~17 GB, qwen35-stamped):
 
 ```bash
-ollama run hf.co/FoolDev/Thanatos-27B           # 17 GB Q4_K_M, qwen36 — fails today, see Heads-up above
+ollama run hf.co/FoolDev/Thanatos-27B           # 17 GB Q4_K_M, qwen35-stamped, loads on stock Ollama
 ```
 
-For 16 GB GPUs / unified-memory laptops — and as a working-today
-fallback while the bundle waits on upstream qwen36 support —
-`make build QUANT=Q3_K_S` downloads the smaller ~12 GB Q3_K_S quant
-from `unsloth/Qwen3.6-27B-GGUF` (qwen35-stamped, loads on every
-current llama.cpp / Ollama build) and creates a local `thanatos-27b`
+For 16 GB GPUs / unified-memory laptops, `make build QUANT=Q3_K_S`
+downloads the smaller ~12 GB Q3_K_S quant from
+`unsloth/Qwen3.6-27B-GGUF` and creates a local `thanatos-27b`
 Ollama tag. Does not redistribute via this repo.
 
 For other quants or local builds, pull from
@@ -258,16 +256,9 @@ python examples/ollama_chat.py      # full demo: chat, streaming, tools, OpenAI-
 
 ### Local apps
 
-The bundled `Thanatos-27B.Q4_K_M.gguf` is `qwen36`-stamped — every row
-below assumes you've rebadged it to `qwen35` per
-[Architecture](#architecture), or that you're pulling a `qwen35`-stamped
-GGUF from `unsloth/Qwen3.6-27B-GGUF` instead. The "fails today with
-`unknown model architecture: 'qwen36'`" caveat applies to every row
-until that's done.
-
 | App | How to load this model |
 |---|---|
-| **Ollama** | `ollama run hf.co/FoolDev/Thanatos-27B` (default Q4_K_M). Pulls the GGUF + the root-level `template` / `system` / `params` files in one step (HF's Ollama bridge ingests these three files; it does **not** read `Modelfile`). For other quants, or to bypass the qwen36 block today, `make build QUANT=Q3_K_S` downloads from unsloth (qwen35-stamped) and creates a local Ollama tag using the `Modelfile`, which is kept in sync with the bridge files. |
+| **Ollama** | `ollama run hf.co/FoolDev/Thanatos-27B` (default Q4_K_M). Pulls the GGUF + the root-level `template` / `system` / `params` files in one step (HF's Ollama bridge ingests these three files; it does **not** read `Modelfile`). For other quants, `make build QUANT=Q3_K_S` downloads from unsloth and creates a local Ollama tag using the `Modelfile`, which is kept in sync with the bridge files. |
 | **LM Studio** | Search → `FoolDev/Thanatos-27B` → pick `Thanatos-27B.Q4_K_M.gguf`. Uses the GGUF's embedded jinja chat template (Qwen 3.6 ChatML); set the system prompt manually from the `SYSTEM` block in this repo's `Modelfile`. |
 | **Jan** | Hub → "Import from Hugging Face" → `FoolDev/Thanatos-27B`. Same template behavior as LM Studio. |
 | **llama.cpp** | `hf download FoolDev/Thanatos-27B Thanatos-27B.Q4_K_M.gguf --local-dir .` then `llama-server -m Thanatos-27B.Q4_K_M.gguf` (or `llama-cli`, `llama-mtmd-cli` for vision via the upstream `mmproj-F16.gguf`). |

scripts/heal_hf_pull.sh

@@ -1,27 +1,22 @@
 #!/usr/bin/env bash
-# Thanatos-27B — heal a freshly pulled HF-bridge tag whose bundled GGUF
-# is `qwen36`-stamped.
+# Thanatos-27B — heal a previously pulled HF-bridge tag whose bundled
+# GGUF is `qwen36`-stamped (legacy v0.6.0-era pulls, before the
+# qwen35 re-stamp in 964e418 / 72259c1).
 #
-# Background. `ollama run hf.co/FoolDev/Thanatos-27B` (or any other
-# qwen36-stamped HF-bridge tag of this repo) pulls a fresh copy of the
-# bundled GGUF every time. Until upstream registers the `qwen36` arch,
-# every such pull fails with `unable to load model: <blob>` (see
-# README "Architecture"). `make load-bundle` works around this by
-# building a *separate* local `thanatos-27b` tag from a rebadged copy,
-# but the canonical HF-bridge tag stays broken.
+# Fresh pulls of `ollama run hf.co/FoolDev/Thanatos-27B` now get the
+# qwen35-stamped bundle and load directly — this script is the
+# recovery path for users who pulled the qwen36-stamped blob into
+# their local Ollama store and haven't refreshed since.
 #
-# This script rebadges the HF-bridge tag's model blob in-place
-# (qwen36 -> qwen35, metadata-only, byte-identical tensors) and
-# rewrites the manifest's model-layer digest to point at the new
-# blob. After running it, `ollama run hf.co/FoolDev/Thanatos-27B`
-# loads.
+# It rebadges the HF-bridge tag's model blob in-place (qwen36 ->
+# qwen35, metadata-only, byte-identical tensors) and rewrites the
+# manifest's model-layer digest to point at the new blob. After
+# running, the cached `hf.co/FoolDev/Thanatos-27B` tag loads.
 #
 # Idempotent: a tag already on qwen35 / qwen35moe is left untouched.
-# Re-runnable after a fresh HF pull (the pull resets the manifest
-# digest back to the qwen36 blob).
-#
-# Once upstream adds the qwen36 arch entry this script (and the
-# whole rebadge dance) can be deleted; the bundle works as-is.
+# The current bundle is qwen35-stamped so this script is a no-op for
+# anyone who pulled after the re-stamp; it stays in the repo for the
+# legacy recovery case.
 #
 # Usage:
 #   ./scripts/heal_hf_pull.sh                                # default tag

scripts/load_bundle.sh

@@ -1,24 +1,23 @@
 #!/usr/bin/env bash
-# Thanatos-27B — load the qwen36-stamped bundle on today's llama.cpp / Ollama.
+# Thanatos-27B — load this repo's bundle into Ollama as a local tag.
 #
-# The bundled GGUF (Thanatos-27B.Q4_K_M.gguf) ships with
-# `general.architecture: 'qwen36'`. No released llama.cpp / Ollama
-# recognizes that arch yet (see README "Architecture"), so a direct
-# `ollama create -f Modelfile` against the bundle fails with
-# `unknown model architecture: 'qwen36'`. This script handles the
-# rebadge workaround end-to-end so users don't have to copy-paste from
-# the README:
+# The bundled GGUF (Thanatos-27B.Q4_K_M.gguf) is qwen35-stamped and
+# loads directly on stock llama.cpp / Ollama. This script is the
+# one-shot path from "I just cloned this repo" to "I have a working
+# local Ollama tag":
 #
 #   1. Resolve the bundle. If it's an LFS pointer (cloned without
 #      `git lfs pull`), download the real ~17 GB blob via `hf download`.
-#   2. Inspect `general.architecture`. If qwen36, rebadge to qwen35
-#      with scripts/rename_arch.py (metadata-only, byte-identical
-#      tensors). If already qwen35, skip the rebadge step.
-#   3. Run `ollama create <tag> -f <temp Modelfile pointing at qwen35>`.
+#   2. Inspect `general.architecture`. If qwen35 / qwen35moe (current
+#      bundle), skip straight to step 3. If qwen36 (legacy v0.6.0-era
+#      checkout), rebadge to qwen35 via scripts/rename_arch.py
+#      (metadata-only, byte-identical tensors).
+#   3. Run `ollama create <tag> -f <temp Modelfile pointing at the
+#      resolved bundle>`.
 #
-# Once upstream adds the qwen36 arch entry the whole workaround
-# disappears — `make build GGUF_PATH=Thanatos-27B.Q4_K_M.gguf` will
-# work directly and this script can be deleted.
+# Useful if you want a bare local tag (`thanatos-27b`) rather than
+# the `hf.co/FoolDev/Thanatos-27B` path. The legacy qwen36 rebadge
+# branch is kept for anyone working from a pre-964e418 checkout.
 #
 # Usage:
 #   ./scripts/load_bundle.sh                 # default tag: thanatos-27b