Instructions to use FoolDev/Janus-35B-HERETIC with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use FoolDev/Janus-35B-HERETIC with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf FoolDev/Janus-35B-HERETIC:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf FoolDev/Janus-35B-HERETIC:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf FoolDev/Janus-35B-HERETIC:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf FoolDev/Janus-35B-HERETIC: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/Janus-35B-HERETIC:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf FoolDev/Janus-35B-HERETIC: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/Janus-35B-HERETIC:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FoolDev/Janus-35B-HERETIC:Q4_K_M

Use Docker

docker model run hf.co/FoolDev/Janus-35B-HERETIC:Q4_K_M

LM Studio
Jan

vLLM

How to use FoolDev/Janus-35B-HERETIC with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FoolDev/Janus-35B-HERETIC"
# 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/Janus-35B-HERETIC",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FoolDev/Janus-35B-HERETIC:Q4_K_M

Ollama
How to use FoolDev/Janus-35B-HERETIC with Ollama:
```
ollama run hf.co/FoolDev/Janus-35B-HERETIC:Q4_K_M
```
Unsloth Desktop

How to use FoolDev/Janus-35B-HERETIC with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FoolDev/Janus-35B-HERETIC:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/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/Janus-35B-HERETIC:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use FoolDev/Janus-35B-HERETIC with Docker Model Runner:
```
docker model run hf.co/FoolDev/Janus-35B-HERETIC:Q4_K_M
```

Lemonade

How to use FoolDev/Janus-35B-HERETIC with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FoolDev/Janus-35B-HERETIC:Q4_K_M

Run and chat with the model

lemonade run user.Janus-35B-HERETIC-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use FoolDev/Janus-35B-HERETIC with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FoolDev/Janus-35B-HERETIC: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/Janus-35B-HERETIC:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use FoolDev/Janus-35B-HERETIC with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FoolDev/Janus-35B-HERETIC:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "FoolDev/Janus-35B-HERETIC:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Janus-35B-HERETIC / scripts /cap_ctx.sh

FoolDev

Claude Opus 5 (1M context)

release 0.9.9: second audit tier — scripts that lied, and card claims that were false

e023532 20 days ago

Raw History Blame Contribute Delete

3.47 kB

	#!/usr/bin/env bash
	# Janus-35B — create a small-context local tag for OpenAI /v1 clients.
	#
	# Ollama's /v1/chat/completions (OpenAI-compatible) silently ignores the
	# `options` field, so it loads at the baked default `num_ctx 262144` — 19.77 GiB
	# of weights plus a 262K f16 KV cache, ~25.4 GiB in total (~23.0 GiB with
	# OLLAMA_KV_CACHE_TYPE=q8_0), which is too much for a tight host. Figures
	# measured 2026-09-18; see the README's Hardware requirements. This bakes a
	# local tag with num_ctx overridden to a loadable value (and num_batch 256),
	# which any OpenAI /v1 client can point at.
	# Reuses this repo's Modelfile verbatim (TEMPLATE / SYSTEM / stop params), only
	# swapping the FROM line to the bundled blob and the num_ctx parameter.
	#
	# Usage:
	# ./scripts/cap_ctx.sh # tag `janus`, num_ctx 4096
	# CTX=8192 TAG=janus-cap ./scripts/cap_ctx.sh
	# GGUF=/path/to/other.gguf ./scripts/cap_ctx.sh
	#
	# Requires: ollama, awk.
	set -euo pipefail

	CTX="${CTX:-4096}"
	NBATCH="${NBATCH:-256}"
	ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
	MODELFILE="${ROOT}/Modelfile"
	GGUF="${GGUF:-${ROOT}/Janus-35B-A3B.Q4_K_M.gguf}"
	TAG="${TAG:-janus}"

	if ! command -v ollama >/dev/null 2>&1; then echo "[!] ollama not found in PATH" >&2; exit 1; fi
	if [[ ! -f "${MODELFILE}" ]]; then echo "[!] missing ${MODELFILE}" >&2; exit 1; fi
	# A fresh clone leaves ${GGUF} on disk as a ~136-byte git-LFS POINTER, not the
	# weights. `[[ -f ]]` is true for that pointer, so the old existence check never
	# fired and `ollama create` was handed a text file. Check the GGUF magic instead.
	if [[ ! -f "${GGUF}" ]] \|\| [[ "$(head -c 4 "${GGUF}" 2>/dev/null)" != "GGUF" ]]; then
	echo "[!] ${GGUF} is not a usable GGUF." >&2
	if [[ -f "${GGUF}" ]]; then
	echo " It looks like an un-smudged git-LFS pointer." >&2
	fi
	echo " Fetch the weights with 'git lfs pull', or run './scripts/load_bundle.sh' - which" >&2
	echo " downloads into .cache/ and prints the path - then rerun with GGUF=<that path>." >&2
	exit 1
	fi

	echo "[*] tag: ${TAG}"
	echo "[*] gguf: ${GGUF}"
	echo "[*] num_ctx: ${CTX} num_batch: ${NBATCH}"

	TMP="$(mktemp -t janus35b-capctx.XXXXXX)"
	trap 'rm -f "${TMP}"' EXIT
	# The END rule is load-bearing: the num_ctx rule only REWRITES an existing
	# PARAMETER num_ctx line, so if the Modelfile ever loses it this script used to
	# emit no override at all and still print "[+] Done. baked at num_ctx=..." - the
	# exact OOM it exists to prevent, reported as success. live_check.sh has carried
	# the same END fallback since 0.6.4.
	awk -v g="${GGUF}" -v c="${CTX}" -v b="${NBATCH}" '
	/^FROM[[:space:]]/ && !done { print "FROM " g; done=1; next }
	/^PARAMETER[[:space:]]+num_ctx[[:space:]]/ { print "PARAMETER num_ctx " c; print "PARAMETER num_batch " b; n=1; next }
	{ print }
	END { if (!n) { print "PARAMETER num_ctx " c; print "PARAMETER num_batch " b } }
	' "${MODELFILE}" > "${TMP}"

	if ! grep -q '^PARAMETER[[:space:]]\+num_ctx[[:space:]]' "${TMP}"; then
	echo "[!] internal error: patched Modelfile carries no num_ctx override" >&2
	exit 1
	fi

	echo "[*] ollama create ${TAG} -f <patched modelfile>"
	ollama create "${TAG}" -f "${TMP}"

	echo
	echo "[+] Done. ${TAG} is baked at num_ctx=${CTX} — usable from any OpenAI /v1 client:"
	echo " curl http://localhost:11434/v1/chat/completions \\"
	echo " -d '{\"model\":\"${TAG}\",\"messages\":[{\"role\":\"user\",\"content\":\"hi\"}]}'"