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

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

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 13 days ago

Commit

124302d

1 Parent(s): e191854

fix(bench.sh): case-insensitive model lookup + Q3_K_S Vulkan run 2 (11.7 tok/s)

Browse files

Surfaced by running `make build QUANT=Q3_K_S` end-to-end for the
first time tonight to validate the friction-free path. Two real
findings:

1. **bench.sh case-sensitivity bug.** `make bench MODEL=thanatos-27b`
errored with "Model 'thanatos-27b' not found" even though
`ollama show thanatos-27b` resolved cleanly and `ollama run
thanatos-27b` worked. Root cause: Ollama 0.24 displays the tag
in /api/tags as `Thanatos-27B:latest` (capitalised) regardless
of the case passed to `ollama create`, but bench.sh's jq check
used `startswith($m)` which is case-sensitive. smoke_test.sh
already uses `ascii_downcase` for the same check (line 54);
bench.sh was the lone holdout. Aligned bench.sh to the same
pattern with an inline comment explaining the Ollama 0.24
quirk.

2. **Q3_K_S Vulkan run 2 data point.** First fresh Q3_K_S bench
since the original Modelfile reference. 11.70 tok/s aggregate
(8009 tokens / 684.0 s; 12.23 / 12.12 / 11.66 short/medium/
long). 4.9% below run 1's 12.31 — within the ±20% noise band
the README hardware section warns about. Slightly longer
per-prompt outputs this run (8009 vs 6182 tokens) plus
late-in-session thermal pressure on the Strix Halo iGPU
explain the gap. Confirms `make build QUANT=Q3_K_S` →
unsloth/Qwen3.6-27B-GGUF → ollama create → bench is a working
end-to-end path on this box.

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

Files changed (2) hide show

Modelfile +11 -1
scripts/bench.sh +6 -1

Modelfile CHANGED Viewed

@@ -136,8 +136,18 @@ Behavior rules:
 # Radeon 8060S iGPU, 32 GB unified, gfx1151, OLLAMA_FLASH_ATTENTION=1,
 # OLLAMA_KV_CACHE_TYPE=q8_0, num_ctx 16384, 3-prompt mix):
 #   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 afternoon)

 # Radeon 8060S iGPU, 32 GB unified, gfx1151, OLLAMA_FLASH_ATTENTION=1,
 # OLLAMA_KV_CACHE_TYPE=q8_0, num_ctx 16384, 3-prompt mix):
 #   Vulkan (OLLAMA_VULKAN=1):
+#     Q3_K_S → 12.31 tok/s aggregate (run 1)
 #       (6182 tokens / 501.9 s; 12.67 / 12.55 / 12.25 short/medium/long)
+#     Q3_K_S → 11.70 tok/s aggregate (run 2, 2026-05-19 evening)
+#       (8009 tokens / 684.0 s; 12.23 / 12.12 / 11.66 short/medium/long)
+#       Second run measured against `thanatos-27b:latest` built via
+#       `make build QUANT=Q3_K_S` — i.e. unsloth/Qwen3.6-27B-GGUF's
+#       qwen35-stamped Q3_K_S, the friction-free path the README
+#       points users at. Aggregate is 4.9% below run 1 (within
+#       the ±20% noise band) — slightly longer per-prompt outputs
+#       this run (8009 vs 6182 tokens) likely contribute the
+#       difference, plus late-in-session thermal pressure on the
+#       Strix Halo iGPU. The friction-free unsloth path works.
 #     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 afternoon)

scripts/bench.sh CHANGED Viewed

@@ -37,7 +37,12 @@ if ! TAGS="$(curl -fsS "${HOST}/api/tags")"; then
     red "[!] Ollama not reachable at ${HOST}"
     exit 1
 fi
-if ! jq -e --arg m "${MODEL}" '.models[] | select(.name | startswith($m))' >/dev/null <<<"${TAGS}"; then
     red "[!] Model '${MODEL}' not found. Build it first: ./scripts/build.sh"
     exit 1
 fi

     red "[!] Ollama not reachable at ${HOST}"
     exit 1
 fi
+# Match case-insensitively: Ollama 0.24's API tag list preserves the
+# case of whatever `general.name` it inferred at create time, which
+# can differ from the case the user passed to `ollama create` / typed
+# into `ollama run`. Both `ollama show <lower>` and `ollama show
+# <Mixed>` resolve to the same model, so the bench check should too.
+if ! jq -e --arg m "${MODEL}" '.models[] | select(.name | ascii_downcase | startswith($m | ascii_downcase))' >/dev/null <<<"${TAGS}"; then
     red "[!] Model '${MODEL}' not found. Build it first: ./scripts/build.sh"
     exit 1
 fi