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 commited on 27 days ago

Commit

82677d0

1 Parent(s): 6f2884f

Fix GGUF filename pattern + correct architecture description

Browse files

- Upstream unsloth/Qwen3.6-27B-GGUF uses dashes (Qwen3.6-27B-Q4_K_M.gguf),
not dots. Without this, scripts/build.sh 404s on first run. Updated
Modelfile, Modelfile.z13, examples/README, examples/llama_cpp_quickstart,
and scripts/build.sh.
- scripts/build.sh: list known-good quant suffixes in a comment so people
don't typo Q4_KM, q4_k_m, etc.
- README architecture section: replace pure-GQA description with the
actual hybrid Gated DeltaNet + Gated Attention layout from the upstream
Qwen3.6 docs; add MTP note and YaRN ~1M ceiling.
- README comparison table: reflect actual Q4_K_M size (17 GB), add Q3_K_S
row, and qualify min-host-memory by quant + context.

Files changed (6) hide show

Modelfile +1 -1
Modelfile.z13 +2 -2
README.md +9 -5
examples/README.md +3 -3
examples/llama_cpp_quickstart.py +1 -1
scripts/build.sh +7 -1

Modelfile CHANGED Viewed

@@ -13,7 +13,7 @@
 #
 # Replace the path below with wherever you keep the GGUF.
-FROM ./Qwen3.6-27B.Q4_K_M.gguf
 # Sampling tuned for reasoning + general use. See README "Recommended sampling"
 # for creative/RP alternatives.

 #
 # Replace the path below with wherever you keep the GGUF.
+FROM ./Qwen3.6-27B-Q4_K_M.gguf
 # Sampling tuned for reasoning + general use. See README "Recommended sampling"
 # for creative/RP alternatives.

Modelfile.z13 CHANGED Viewed

@@ -8,7 +8,7 @@
 #      and we compensate with top_k instead.
 #
 # Recommended base GGUF for this profile:
-#   https://huggingface.co/unsloth/Qwen3.6-27B-GGUF -> Qwen3.6-27B.Q3_K_S.gguf
 #
 # Usage:
 #   ollama create janus-27b-z13 -f Modelfile.z13
@@ -20,7 +20,7 @@
 #   export OLLAMA_NUM_PARALLEL=1          # don't fan out across requests
 #   export HSA_OVERRIDE_GFX_VERSION=11.5.1 # if ROCm doesn't auto-detect gfx1150
-FROM ./Qwen3.6-27B.Q3_K_S.gguf
 PARAMETER temperature 0.6
 PARAMETER top_p 0.95

 #      and we compensate with top_k instead.
 #
 # Recommended base GGUF for this profile:
+#   https://huggingface.co/unsloth/Qwen3.6-27B-GGUF -> Qwen3.6-27B-Q3_K_S.gguf
 #
 # Usage:
 #   ollama create janus-27b-z13 -f Modelfile.z13
 #   export OLLAMA_NUM_PARALLEL=1          # don't fan out across requests
 #   export HSA_OVERRIDE_GFX_VERSION=11.5.1 # if ROCm doesn't auto-detect gfx1150
+FROM ./Qwen3.6-27B-Q3_K_S.gguf
 PARAMETER temperature 0.6
 PARAMETER top_p 0.95

README.md CHANGED Viewed

@@ -71,8 +71,9 @@ The 27B is **dense**: every parameter participates in every forward pass. It's s
 | Active params per token | 27 B | ~3 B |
 | Layers | 64 | 40 |
 | Hidden size | 5120 | 2048 |
-| Q4_K_M GGUF size | ~16 GB | ~19 GB |
-| Min host memory | ~24 GB | ~38 GB |
 | Multimodal | Yes (vision) | Yes (vision) |
 | Max context | 262 144 | 262 144 |
@@ -96,11 +97,14 @@ If you want the safetensors for `transformers`, fetch them from [`Qwen/Qwen3.6-2
 ## Architecture
 - Qwen 3.6 dense, 27B parameters, 64 transformer layers
-- 24 attention heads, 4 KV heads (GQA), head_dim 256
-- Hidden size 5120, intermediate size 17408 (~3.4× ratio)
 - Vocab 248,320 (shared with 35B-A3B sibling)
-- 262k native context, extensible with YaRN
 - Vision + video support via upstream `mmproj` (not in this repo)
 ## Quick start

 | Active params per token | 27 B | ~3 B |
 | Layers | 64 | 40 |
 | Hidden size | 5120 | 2048 |
+| Q4_K_M GGUF size | ~17 GB | ~19 GB |
+| Q3_K_S GGUF size | ~12 GB | n/a |
+| Min host memory @ Q4 / 8K ctx | ~22 GB | ~38 GB |
 | Multimodal | Yes (vision) | Yes (vision) |
 | Max context | 262 144 | 262 144 |
 ## Architecture
 - Qwen 3.6 dense, 27B parameters, 64 transformer layers
+- **Hybrid attention stack**: 16 repeats of `[3 × (Gated DeltaNet → FFN) → 1 × (Gated Attention → FFN)]`
+  - Gated DeltaNet (linear attention): 48 V-heads, 16 QK-heads, head_dim 128
+  - Gated Attention (softmax): 24 Q-heads, 4 KV-heads (GQA), head_dim 256, partial RoPE (factor 0.25)
+- Hidden size 5120, FFN intermediate 17408 (~3.4× ratio)
 - Vocab 248,320 (shared with 35B-A3B sibling)
+- 262 144 native context, extensible to ~1 M with YaRN
 - Vision + video support via upstream `mmproj` (not in this repo)
+- Multi-token prediction (MTP) head trained for speculative decoding
 ## Quick start

examples/README.md CHANGED Viewed

@@ -18,9 +18,9 @@ be consistent across backends modulo quantization noise.
 ```bash
 # 1. Pull a Qwen 3.6 27B GGUF, e.g. unsloth/Qwen3.6-27B-GGUF
-hf download unsloth/Qwen3.6-27B-GGUF Qwen3.6-27B.Q4_K_M.gguf --local-dir .
-# 2. Edit ../Modelfile -> FROM ./Qwen3.6-27B.Q4_K_M.gguf
 # 3. Build the model
 ollama create janus-27b -f ../Modelfile
@@ -42,7 +42,7 @@ python transformers_quickstart.py --no-4bit  # bf16, ~54 GB VRAM
 ```bash
 pip install llama-cpp-python  # CPU-only build
-python llama_cpp_quickstart.py /path/to/Qwen3.6-27B.Q4_K_M.gguf --gpu-layers 99
 ```
 For GPU offload, rebuild llama-cpp-python with the matching backend — see

 ```bash
 # 1. Pull a Qwen 3.6 27B GGUF, e.g. unsloth/Qwen3.6-27B-GGUF
+hf download unsloth/Qwen3.6-27B-GGUF Qwen3.6-27B-Q4_K_M.gguf --local-dir .
+# 2. Edit ../Modelfile -> FROM ./Qwen3.6-27B-Q4_K_M.gguf
 # 3. Build the model
 ollama create janus-27b -f ../Modelfile
 ```bash
 pip install llama-cpp-python  # CPU-only build
+python llama_cpp_quickstart.py /path/to/Qwen3.6-27B-Q4_K_M.gguf --gpu-layers 99
 ```
 For GPU offload, rebuild llama-cpp-python with the matching backend — see

examples/llama_cpp_quickstart.py CHANGED Viewed

@@ -14,7 +14,7 @@ For GPU offload (CUDA / Metal / ROCm), install with the matching extras:
     CMAKE_ARGS="-DGGML_HIPBLAS=on" pip install llama-cpp-python --no-binary :all:
 Usage:
-    python llama_cpp_quickstart.py /path/to/Qwen3.6-27B.Q4_K_M.gguf
     python llama_cpp_quickstart.py /path/to/file.gguf --gpu-layers 99
     python llama_cpp_quickstart.py /path/to/file.gguf --prompt "..."
 """

     CMAKE_ARGS="-DGGML_HIPBLAS=on" pip install llama-cpp-python --no-binary :all:
 Usage:
+    python llama_cpp_quickstart.py /path/to/Qwen3.6-27B-Q4_K_M.gguf
     python llama_cpp_quickstart.py /path/to/file.gguf --gpu-layers 99
     python llama_cpp_quickstart.py /path/to/file.gguf --prompt "..."
 """

scripts/build.sh CHANGED Viewed

@@ -14,7 +14,13 @@ QUANT="${1:-${QUANT:-Q4_K_M}}"
 PROFILE="${2:-${PROFILE:-default}}"
 REPO_ID="${REPO_ID:-unsloth/Qwen3.6-27B-GGUF}"
-GGUF_NAME="Qwen3.6-27B.${QUANT}.gguf"
 ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
 GGUF_PATH="${ROOT}/${GGUF_NAME}"

 PROFILE="${2:-${PROFILE:-default}}"
 REPO_ID="${REPO_ID:-unsloth/Qwen3.6-27B-GGUF}"
+# Upstream uses dashes, e.g. Qwen3.6-27B-Q4_K_M.gguf. Quants known to exist
+# at unsloth/Qwen3.6-27B-GGUF (as of 2026-04):
+#   Q3_K_S Q3_K_M Q4_0 Q4_1 Q4_K_S Q4_K_M Q5_K_S Q5_K_M Q6_K Q8_0
+#   IQ4_XS IQ4_NL
+#   UD-IQ2_XXS UD-IQ2_M UD-Q2_K_XL UD-IQ3_XXS UD-Q3_K_XL UD-Q4_K_XL
+#   UD-Q5_K_XL UD-Q6_K_XL UD-Q8_K_XL
+GGUF_NAME="Qwen3.6-27B-${QUANT}.gguf"
 ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
 GGUF_PATH="${ROOT}/${GGUF_NAME}"