Instructions to use FoolDev/Thanatos-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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
bench.sh: simplify per code-review findings
Browse files- Drop NPROMPTS=5 from the usage docstring — the variable was never
read; the example was a lie.
- Extract the duplicated 'jq tok/s math' expression into a tok_per_s()
helper. Two callers, identical formula — one place to fix if the
rounding ever needs to change.
- Route red() error output to stderr instead of stdout. Callers parsing
the table off stdout shouldn't see error noise mixed in.
- Cache the /api/tags response into TAGS once and reuse for both the
reachability check and the model-present jq filter, instead of
hitting the endpoint twice back-to-back.
Behavior unchanged on the happy path; failure messages now redirect
to stderr (verified with MODEL=nonexistent-model).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- scripts/bench.sh +12 -6
|
@@ -8,7 +8,7 @@
|
|
| 8 |
#
|
| 9 |
# Usage:
|
| 10 |
# ./scripts/bench.sh # uses MODEL=janus-27b
|
| 11 |
-
# MODEL=janus-27b
|
| 12 |
# HOST=http://localhost:11434 ./scripts/bench.sh
|
| 13 |
#
|
| 14 |
# Requires: curl, jq, a running Ollama daemon with the model created.
|
|
@@ -17,21 +17,27 @@ set -euo pipefail
|
|
| 17 |
MODEL="${MODEL:-janus-27b}"
|
| 18 |
HOST="${HOST:-http://localhost:11434}"
|
| 19 |
|
| 20 |
-
red() { printf "\033[31m%s\033[0m\n" "$*"; }
|
| 21 |
green() { printf "\033[32m%s\033[0m\n" "$*"; }
|
| 22 |
blue() { printf "\033[34m%s\033[0m\n" "$*"; }
|
| 23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
for dep in curl jq; do
|
| 25 |
if ! command -v "$dep" >/dev/null 2>&1; then
|
| 26 |
red "[!] missing dependency: $dep"; exit 1
|
| 27 |
fi
|
| 28 |
done
|
| 29 |
|
| 30 |
-
|
|
|
|
| 31 |
red "[!] Ollama not reachable at ${HOST}"
|
| 32 |
exit 1
|
| 33 |
fi
|
| 34 |
-
if !
|
| 35 |
red "[!] Model '${MODEL}' not found. Build it first: ./scripts/build.sh"
|
| 36 |
exit 1
|
| 37 |
fi
|
|
@@ -86,7 +92,7 @@ for i in "${!PROMPTS[@]}"; do
|
|
| 86 |
fi
|
| 87 |
|
| 88 |
eval_ms=$(( eval_ns / 1000000 ))
|
| 89 |
-
toks_per_s="$(
|
| 90 |
printf "%-4s %8s %12s %8s\n" "$((i+1))" "$eval_count" "$eval_ms" "$toks_per_s"
|
| 91 |
|
| 92 |
TOTAL_TOKENS=$(( TOTAL_TOKENS + eval_count ))
|
|
@@ -94,5 +100,5 @@ for i in "${!PROMPTS[@]}"; do
|
|
| 94 |
done
|
| 95 |
|
| 96 |
echo
|
| 97 |
-
avg="$(
|
| 98 |
green "[+] aggregate: ${TOTAL_TOKENS} tokens / $(( TOTAL_NS / 1000000 )) ms = ${avg} tok/s"
|
|
|
|
| 8 |
#
|
| 9 |
# Usage:
|
| 10 |
# ./scripts/bench.sh # uses MODEL=janus-27b
|
| 11 |
+
# MODEL=janus-27b ./scripts/bench.sh
|
| 12 |
# HOST=http://localhost:11434 ./scripts/bench.sh
|
| 13 |
#
|
| 14 |
# Requires: curl, jq, a running Ollama daemon with the model created.
|
|
|
|
| 17 |
MODEL="${MODEL:-janus-27b}"
|
| 18 |
HOST="${HOST:-http://localhost:11434}"
|
| 19 |
|
| 20 |
+
red() { printf "\033[31m%s\033[0m\n" "$*" >&2; }
|
| 21 |
green() { printf "\033[32m%s\033[0m\n" "$*"; }
|
| 22 |
blue() { printf "\033[34m%s\033[0m\n" "$*"; }
|
| 23 |
|
| 24 |
+
# tok_per_s <eval_count> <eval_duration_ns> -> "X.YZ" (2 dp, floor).
|
| 25 |
+
tok_per_s() {
|
| 26 |
+
jq -n --argjson c "$1" --argjson n "$2" '($c / ($n / 1e9)) | . * 100 | floor / 100'
|
| 27 |
+
}
|
| 28 |
+
|
| 29 |
for dep in curl jq; do
|
| 30 |
if ! command -v "$dep" >/dev/null 2>&1; then
|
| 31 |
red "[!] missing dependency: $dep"; exit 1
|
| 32 |
fi
|
| 33 |
done
|
| 34 |
|
| 35 |
+
# Single /api/tags fetch covers both checks below.
|
| 36 |
+
if ! TAGS="$(curl -fsS "${HOST}/api/tags")"; then
|
| 37 |
red "[!] Ollama not reachable at ${HOST}"
|
| 38 |
exit 1
|
| 39 |
fi
|
| 40 |
+
if ! jq -e --arg m "${MODEL}" '.models[] | select(.name | startswith($m))' >/dev/null <<<"${TAGS}"; then
|
| 41 |
red "[!] Model '${MODEL}' not found. Build it first: ./scripts/build.sh"
|
| 42 |
exit 1
|
| 43 |
fi
|
|
|
|
| 92 |
fi
|
| 93 |
|
| 94 |
eval_ms=$(( eval_ns / 1000000 ))
|
| 95 |
+
toks_per_s="$(tok_per_s "$eval_count" "$eval_ns")"
|
| 96 |
printf "%-4s %8s %12s %8s\n" "$((i+1))" "$eval_count" "$eval_ms" "$toks_per_s"
|
| 97 |
|
| 98 |
TOTAL_TOKENS=$(( TOTAL_TOKENS + eval_count ))
|
|
|
|
| 100 |
done
|
| 101 |
|
| 102 |
echo
|
| 103 |
+
avg="$(tok_per_s "$TOTAL_TOKENS" "$TOTAL_NS")"
|
| 104 |
green "[+] aggregate: ${TOTAL_TOKENS} tokens / $(( TOTAL_NS / 1000000 )) ms = ${avg} tok/s"
|