Instructions to use FoolDev/Thanatos-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FoolDev/Thanatos-27B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="FoolDev/Thanatos-27B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("FoolDev/Thanatos-27B", dtype="auto")

llama-cpp-python

How to use FoolDev/Thanatos-27B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="FoolDev/Thanatos-27B",
	filename="Thanatos-27B.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use FoolDev/Thanatos-27B with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf FoolDev/Thanatos-27B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf FoolDev/Thanatos-27B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf FoolDev/Thanatos-27B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf FoolDev/Thanatos-27B:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf FoolDev/Thanatos-27B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf FoolDev/Thanatos-27B:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf FoolDev/Thanatos-27B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FoolDev/Thanatos-27B:Q4_K_M

Use Docker

docker model run hf.co/FoolDev/Thanatos-27B:Q4_K_M

LM Studio
Jan

vLLM

How to use FoolDev/Thanatos-27B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FoolDev/Thanatos-27B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FoolDev/Thanatos-27B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/FoolDev/Thanatos-27B:Q4_K_M

SGLang

How to use FoolDev/Thanatos-27B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "FoolDev/Thanatos-27B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FoolDev/Thanatos-27B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "FoolDev/Thanatos-27B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FoolDev/Thanatos-27B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use FoolDev/Thanatos-27B with Ollama:
```
ollama run hf.co/FoolDev/Thanatos-27B:Q4_K_M
```

Unsloth Studio new

How to use FoolDev/Thanatos-27B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for FoolDev/Thanatos-27B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for FoolDev/Thanatos-27B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for FoolDev/Thanatos-27B to start chatting

Pi new

How to use FoolDev/Thanatos-27B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf FoolDev/Thanatos-27B:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "FoolDev/Thanatos-27B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use FoolDev/Thanatos-27B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf FoolDev/Thanatos-27B:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default FoolDev/Thanatos-27B:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use FoolDev/Thanatos-27B with Docker Model Runner:
```
docker model run hf.co/FoolDev/Thanatos-27B:Q4_K_M
```

Lemonade

How to use FoolDev/Thanatos-27B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FoolDev/Thanatos-27B:Q4_K_M

Run and chat with the model

lemonade run user.Thanatos-27B-Q4_K_M

List all available models

lemonade list

FoolDev Claude Opus 4.7 commited on 10 days ago

Commit

1c88b41

1 Parent(s): 964e418

docs: align README + CHANGELOG with the qwen35 re-stamp (964e418)

Browse files

964e418 (HF-direct `hf upload`) re-stamped the bundled
Thanatos-27B.Q4_K_M.gguf from `general.architecture: 'qwen36'`
back to `'qwen35'`, byte-identical tensors. This commit catches
the docs up:

- README "Heads up" callout removed. It warned about a load
failure that no longer exists, so it was actively misleading.
- README TL;DR collapsed from "three paths around it" back to a
single one-liner. `ollama run hf.co/FoolDev/Thanatos-27B` now
loads on stock Ollama. `make heal-hf` kept as a one-sentence
callout for anyone who already pulled the v0.6.0 (qwen36)
bundle and has the broken blob in their store.
- CHANGELOG [Unreleased] gets a Changed entry documenting the
re-flip + the new bundle blob sha
(5ed60d0af4650a854b1755bd392f9aef4872643dc25a254bc68043fa638392a0,
same hash `make load-bundle` / `make heal-hf` have been
producing locally all session).

Intentionally left stale this commit (follow-up):

- README "Architecture" section still has the long qwen36
narrative + "upstream-may-never-adopt" subagent note.
- Quick start Ollama section still has option A "fails today"
warning.
- examples/README still leads with `make heal-hf` after pull.
- Modelfile preamble (if any) qwen36 mentions.

Those don't actively mislead — the workarounds still work and
are still wired up — they're just over-prominent for a model
that now loads straight. A separate pass can collapse them.

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

Files changed (2) hide show

CHANGELOG.md +35 -0
README.md +8 -36

CHANGELOG.md CHANGED Viewed

@@ -7,6 +7,41 @@ and documentation**, not the underlying base model.
 ## [Unreleased]
 ### 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).

 ## [Unreleased]
+### Changed
+- **Bundle re-stamped `general.architecture: 'qwen36'` → `'qwen35'`**
+  in commit 964e418 (HF-direct `hf upload`). Reverses the v0.6.0
+  `qwen36` stamp from e1f78fa, which itself flipped qwen35 → qwen36
+  deliberately. The proximate trigger: today's subagent recheck
+  found no PR or tracking issue for a `qwen36` arch entry in either
+  `ggml-org/llama.cpp` or `ollama/ollama`, and the actual Qwen 3.6
+  family upstream already loads under `qwen35moe` — so the qwen36
+  stamp was going to stay ahead-of-upstream indefinitely, not for a
+  release or two. Day-to-day cost (every fresh
+  `ollama run hf.co/FoolDev/Thanatos-27B` hitting a 500, every user
+  needing `make heal-hf` to recover) outweighed the
+  architectural-honesty benefit. Tensor data stays byte-identical;
+  only the `general.architecture` KV (and the namespaced KV keys)
+  flips. New bundle blob SHA is
+  `5ed60d0af4650a854b1755bd392f9aef4872643dc25a254bc68043fa638392a0`
+  — the same hash `make load-bundle` and `make heal-hf` have been
+  producing locally this whole session.
+- README "Heads up" callout (qwen36 load-failure warning) removed.
+  TL;DR collapsed back from "three paths around it" to a single
+  one-liner: `ollama run hf.co/FoolDev/Thanatos-27B` now loads on
+  stock Ollama. `make heal-hf` is mentioned as the recovery path
+  for anyone who pulled the v0.6.0 bundle and still has the qwen36
+  blob in their store.
+### Note
+- `make heal-hf`, `make load-bundle`, and `scripts/rename_arch.py`
+  stay in the repo and stay useful. heal-hf is idempotent on qwen35
+  (skips early); load-bundle does a no-op rebadge on a qwen35 bundle
+  and runs `ollama create` as normal. The deeper Architecture /
+  Quick start / examples-README narrative still talks about the
+  qwen36 stamp and the workaround dance; left intentionally stale
+  in this commit for follow-up cleanup, since the immediate user
+  pain (load 500 on fresh pull) is what the upload commit fixed.
 ### 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).

README.md CHANGED Viewed

@@ -61,16 +61,6 @@ pipeline_tag: image-text-to-text
 A personal sibling to [`FoolDev/Janus-35B`](https://huggingface.co/FoolDev/Janus-35B). Same teacher (Claude Opus 4.7), same dataset family, but built on the **dense** [Qwen/Qwen3.6-27B](https://huggingface.co/Qwen/Qwen3.6-27B) base instead of the 35B-A3B MoE. Smaller, easier to deploy, no expert-routing surprises.
-> ⚠️ **Heads up — bundle is stamped `qwen36`.** As of 2026-05-19 the
-> bundled GGUF declares `general.architecture: 'qwen36'`, which no
-> released llama.cpp / Ollama recognizes yet. `ollama run
-> hf.co/FoolDev/Thanatos-27B` and `llama-server -m
-> Thanatos-27B.Q4_K_M.gguf` both fail today with `unknown model
-> architecture: 'qwen36'`. Workaround in one line:
-> `git clone … && cd Thanatos-27B && make load-bundle && ollama run
-> thanatos-27b`. Details in [Architecture](#architecture). Once
-> upstream ships qwen36 the workaround disappears.
 ## TL;DR
 One-liner via Hugging Face (pulls a GGUF + this repo's root-level
@@ -79,40 +69,22 @@ template — HF's Ollama bridge ingests those three files, not
 `Modelfile`):
 ```bash
-ollama run hf.co/FoolDev/Thanatos-27B           # ~17 GB Q4_K_M, qwen36-stamped (see Heads-up above)
 ```
-That command fails today with `unknown model architecture: 'qwen36'`
-because the bundle is qwen36-stamped. Three paths around it (all
-require this repo cloned):
 ```bash
 git clone https://huggingface.co/FoolDev/Thanatos-27B && cd Thanatos-27B
-# A. Already ran the broken pull? Heal it in place — rebadges the
-#    already-downloaded blob's arch metadata + rewrites the manifest
-#    digest so `ollama run hf.co/FoolDev/Thanatos-27B` loads:
-make heal-hf
-ollama run hf.co/FoolDev/Thanatos-27B
-# B. Haven't pulled yet — load *this repo's* qwen36-stamped bundle
-#    via the rebadge helper (smudges LFS if needed, rebadges
-#    qwen36 → qwen35, runs `ollama create thanatos-27b`):
-make load-bundle
-ollama run thanatos-27b
-# C. Bypass the bundle: download a qwen35-stamped GGUF from unsloth
-#    and build locally. Loads on every current llama.cpp / Ollama.
-make build                              # Q4_K_M from unsloth
-make build QUANT=Q3_K_S                  # 12 GB smaller quant
-make build QUANT=Q5_K_M                  # 20 GB higher quality
 ollama run thanatos-27b
 ```
-Once upstream adds the qwen36 arch entry, all three paths collapse
-to the direct `ollama run hf.co/FoolDev/Thanatos-27B` one-liner
-above.
 For other quants (Q3_K_S ~12 GB, Q5_K_M ~20 GB, etc.), `make build
 QUANT=Q3_K_S` is the simplest path. See [Quick start](#quick-start)
 below for the full matrix.

 A personal sibling to [`FoolDev/Janus-35B`](https://huggingface.co/FoolDev/Janus-35B). Same teacher (Claude Opus 4.7), same dataset family, but built on the **dense** [Qwen/Qwen3.6-27B](https://huggingface.co/Qwen/Qwen3.6-27B) base instead of the 35B-A3B MoE. Smaller, easier to deploy, no expert-routing surprises.
 ## TL;DR
 One-liner via Hugging Face (pulls a GGUF + this repo's root-level
 `Modelfile`):
 ```bash
+ollama run hf.co/FoolDev/Thanatos-27B           # ~17 GB Q4_K_M, qwen35-stamped, loads on stock Ollama
 ```
+If you pulled the bundle while it was qwen36-stamped (v0.6.0
+through the early hours of 2026-05-19) the load will still 500 on
+that stale blob — `make heal-hf` rebadges it in place. Fresh
+pulls after this fix go straight through.
+For other quants (Q3_K_S ~12 GB, Q5_K_M ~20 GB, etc.):
 ```bash
 git clone https://huggingface.co/FoolDev/Thanatos-27B && cd Thanatos-27B
+make build QUANT=Q3_K_S                  # downloads from unsloth/Qwen3.6-27B-GGUF
 ollama run thanatos-27b
 ```
 For other quants (Q3_K_S ~12 GB, Q5_K_M ~20 GB, etc.), `make build
 QUANT=Q3_K_S` is the simplest path. See [Quick start](#quick-start)
 below for the full matrix.