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

7063e20

1 Parent(s): a51a43a

docs: second Q4_K_M Vulkan bench data point (9.19 tok/s, post-heal)

Browse files

Bench reconfirmation against the qwen36-stamped HF-bridge tag after
`make heal-hf` rebadged its model blob to qwen35 in store. Same
Strix Halo hardware and config as the existing 9.31 tok/s entry
(ROG Flow Z13 GZ302EA / Ryzen AI Max+ 395 + Radeon 8060S iGPU,
gfx1151, OLLAMA_FLASH_ATTENTION=1, OLLAMA_KV_CACHE_TYPE=q8_0,
OLLAMA_VULKAN=1, num_ctx 16384, 3-prompt mix):

Q4_K_M -> 9.19 tok/s aggregate
(6210 tokens / 675.6 s; 9.40 / 9.29 / 9.16 short/medium/long)

The point isn't the number — it's that the heal-hf path produces a
performance-equivalent model to load-bundle. 1.3% below run 1, well
inside the ±20% noise band the README hardware section already
warns about. The longer outputs this run (6210 vs 5356 tokens)
account for most of the wall-time difference; per-step throughput
held steady.

Modelfile hardware-notes block now lists two parallel Q4_K_M
Vulkan data points instead of one — establishes the band rather
than the point.

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

Files changed (2) hide show

CHANGELOG.md +11 -0
Modelfile +9 -1

CHANGELOG.md CHANGED Viewed

@@ -32,6 +32,17 @@ and documentation**, not the underlying base model.
   (`make build`). New `scripts/heal_hf_pull.sh` entry added to the
   "What's here" table.
 ### Changed
 - README "Architecture" section + Quick start option A:
   - Architecture body now notes that neither `ggml-org/llama.cpp`

   (`make build`). New `scripts/heal_hf_pull.sh` entry added to the
   "What's here" table.
+### Added
+- Second Q4_K_M Vulkan bench data point on the Strix Halo reference
+  hardware (same machine + config as the existing 9.31 tok/s entry):
+  **9.19 tok/s aggregate** (6210 tokens / 675.6 s; 9.40 / 9.29 / 9.16
+  short/medium/long). Measured 2026-05-19 against the qwen36-stamped
+  HF-bridge tag after `make heal-hf` rebadged it to qwen35 in
+  store — confirms the in-place heal produces a model with the same
+  performance profile as `make load-bundle`. Aggregate is 1.3% below
+  the existing run-1 (9.31), well inside the ±20% noise band the
+  README warns about. Modelfile hardware notes updated.
 ### Changed
 - README "Architecture" section + Quick start option A:
   - Architecture body now notes that neither `ggml-org/llama.cpp`

Modelfile CHANGED Viewed

@@ -145,8 +145,16 @@ Behavior rules:
 #   Vulkan (OLLAMA_VULKAN=1):
 #     Q3_K_S → 12.31 tok/s aggregate
 #       (6182 tokens / 501.9 s; 12.67 / 12.55 / 12.25 short/medium/long)
-#     Q4_K_M →  9.31 tok/s aggregate
 #       (5356 tokens / 574.9 s;  9.48 /  9.43 /  9.28 short/medium/long)
 #   ROCm (older snapshot, kept for backend comparison):
 #     Q3_K_S → 10.14 tok/s aggregate
 #       (8080 tokens / 796.5 s; 10.37 / 10.31 / 10.11 short/medium/long)

 #   Vulkan (OLLAMA_VULKAN=1):
 #     Q3_K_S → 12.31 tok/s aggregate
 #       (6182 tokens / 501.9 s; 12.67 / 12.55 / 12.25 short/medium/long)
+#     Q4_K_M →  9.31 tok/s aggregate (run 1)
 #       (5356 tokens / 574.9 s;  9.48 /  9.43 /  9.28 short/medium/long)
+#     Q4_K_M →  9.19 tok/s aggregate (run 2, 2026-05-19)
+#       (6210 tokens / 675.6 s;  9.40 /  9.29 /  9.16 short/medium/long)
+#       Second run measured against the qwen36-stamped HF-bridge tag
+#       after `make heal-hf` rebadged it to qwen35 in store — confirms
+#       the in-place heal produces a model with the same performance
+#       profile as `make load-bundle`. Aggregate is 1.3% below run 1
+#       (within the ±20% noise band the README hardware section
+#       warns about).
 #   ROCm (older snapshot, kept for backend comparison):
 #     Q3_K_S → 10.14 tok/s aggregate
 #       (8080 tokens / 796.5 s; 10.37 / 10.31 / 10.11 short/medium/long)