Instructions to use ajvikram/cranebear-vlm-4b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ajvikram/cranebear-vlm-4b-gguf 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 ajvikram/cranebear-vlm-4b-gguf:F16
# Run inference directly in the terminal:
llama cli -hf ajvikram/cranebear-vlm-4b-gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ajvikram/cranebear-vlm-4b-gguf:F16
# Run inference directly in the terminal:
llama cli -hf ajvikram/cranebear-vlm-4b-gguf:F16

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 ajvikram/cranebear-vlm-4b-gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf ajvikram/cranebear-vlm-4b-gguf:F16

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 ajvikram/cranebear-vlm-4b-gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ajvikram/cranebear-vlm-4b-gguf:F16

Use Docker

docker model run hf.co/ajvikram/cranebear-vlm-4b-gguf:F16

LM Studio
Jan

vLLM

How to use ajvikram/cranebear-vlm-4b-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ajvikram/cranebear-vlm-4b-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ajvikram/cranebear-vlm-4b-gguf",
		"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/ajvikram/cranebear-vlm-4b-gguf:F16

Ollama
How to use ajvikram/cranebear-vlm-4b-gguf with Ollama:
```
ollama run hf.co/ajvikram/cranebear-vlm-4b-gguf:F16
```
Unsloth Desktop

How to use ajvikram/cranebear-vlm-4b-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ajvikram/cranebear-vlm-4b-gguf:F16

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": "ajvikram/cranebear-vlm-4b-gguf:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ajvikram/cranebear-vlm-4b-gguf with Docker Model Runner:
```
docker model run hf.co/ajvikram/cranebear-vlm-4b-gguf:F16
```

Lemonade

How to use ajvikram/cranebear-vlm-4b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ajvikram/cranebear-vlm-4b-gguf:F16

Run and chat with the model

lemonade run user.cranebear-vlm-4b-gguf-F16

List all available models

lemonade list

Hermes Agent

How to use ajvikram/cranebear-vlm-4b-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ajvikram/cranebear-vlm-4b-gguf:F16

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 ajvikram/cranebear-vlm-4b-gguf:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ajvikram/cranebear-vlm-4b-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ajvikram/cranebear-vlm-4b-gguf:F16

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 "ajvikram/cranebear-vlm-4b-gguf:F16" \
  --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"

CraneBear VLM 4B (GGUF) — transcript + optional photo → extraction JSON

A LoRA fine-tune of Qwen3-VL-4B-Instruct that turns a panic emergency voice transcript, with an optional photo, into the same 7-key extraction JSON the CraneBear text model emits, for a human dispatcher. Ships as a Q4_K_M text GGUF plus an f16 multimodal projector, for llama.cpp / llama-server / the iOS mtmd path.

The model extracts. A human decides. It never triages, dispatches, or advises. Severity bands are evidence labels for a trained dispatcher.

This repo replaces ajvikram/emergency-vision-triage-2b-gguf, which was a text-only decoder with no vision tower despite its name (documented in the training write-up); that repo is deprecated.

Two checkpoints

File	Use it for	24-case held-out set (partner's, text-only)
`vlm-v2-r2-q4_k_m.gguf`	best text extraction (no photo)	93.8% macro, 0% missed-IMMEDIATE (raw 92.7%)
`vlm-v2-r3-q4_k_m.gguf` + `mmproj-vlm-v2-r3-f16.gguf`	transcript + photo	91.7% macro, 0% missed-IMMEDIATE (raw 88.5%)

For reference, the partner's production text model (cranebear-extraction-4b, round 3) scores 91.7% / 0% on the same set, on-contract. Both checkpoints here were trained on the same 800-row round-3 text set; r3 adds 1,018 (transcript, photo) pairs.

Status: what is and is not established

Established, measured:

Text contract: both checkpoints pass the partner's blocking gate (0% missed-IMMEDIATE, asserted) and the ≥90% macro gate on their 24-case set.
The vision path is real: r3 reads hazards from photos (7/7 on the photo-adds slice of a 60-case photo set), ignores irrelevant photos in 14/18 cases, and over-triages far less than a text-only checkpoint shown the same photos (false-IMMEDIATE 3/16 vs 16/31).
Served through llama-server and through the partner's Swift/mtmd path, the two stacks agree on these numbers.

Not established — do not treat as production-safe for photo input yet:

The 60-case photo eval set carries proposed, unratified labels and only 34 sourced photos. On it, r3 still has 1 missed-IMMEDIATE, 1 photo-subtracted severity, 2 photo-only HIGH confidences.
Those last two classes go to zero for every checkpoint when the caller applies the text-first merge (below). That merge is a caller-side guardrail; it is not inside the weights.
The photo training taught four rules (a photo may add a hazard; a photo never subtracts; photo-only evidence never HIGH; an irrelevant photo changes nothing). It did not teach a photo supplying a rule-1 sign (a person under rubble) or a casualty count — no public image set covers that ethically.
Never run on a phone. All numbers are llama.cpp on a Mac.

Serving contract (must match exactly)

Prompt: the SYSTEM text in Modelfile.vlm-v2-r3 (byte-identical to the CraneBear text model's round-3 prompt). With a photo, append the paragraph in photo_addendum.py to the system prompt and place the image before Transcript: in the user turn.
No think block. Qwen3-VL-Instruct's template has none; rendering one is a served/trained mismatch.
Grammar: cranebear-extraction-presence.gbnf. The model emits a presence-encoded object (no nulls); the consumer maps sentinels to nulls.
Greedy (temperature 0). Photos downscaled to 512 px longest side (~200 image tokens).

llama-server -m vlm-v2-r3-q4_k_m.gguf --mmproj mmproj-vlm-v2-r3-f16.gguf -c 4096 -ngl 99
# POST /v1/chat/completions with the system prompt (+ addendum), an image_url
# content part, "Transcript:\n<text>", and "grammar": <the gbnf>.

Recommended caller-side merge for photo input (what the partner's Guardrails.mergePhoto does): run the text-only pass first, then the photo pass; take severity = max on MINOR < DELAYED < IMMEDIATE (DECEASED only from text), OR the hazard bits, keep a stated casualty count, and cap photo-only severity confidence at MEDIUM. Measured: this removes every "photo subtracted" and "photo-only HIGH" case for every checkpoint tested.

Training

Base Qwen/Qwen3-VL-4B-Instruct (16-bit), LoRA r=16 on the language tower, vision encoder frozen, early stopping on eval loss, best checkpoint loaded.
r2: 800 text rows (partner-schema, presence-encoded), 4 epochs, ~3.4 h.
r3: + 1,018 photo pairs from 880 Wikimedia Commons photos (CC0 / CC BY / CC BY-SA / PD, recorded per file) with deterministic labels derived from each photo's category and the four photo rules — no teacher model. 300 steps, ~6.9 h. mmproj is byte-identical to the base's (frozen tower).
Hardware: NVIDIA DGX Spark (GB10). Reproduction scripts, data engines, eval harnesses and the full round-by-round record (including a documented negative round 4) live in the slm-factory repo.

Files

vlm-v2-r2-q4_k_m.gguf, vlm-v2-r3-q4_k_m.gguf — text models (Q4_K_M, 2.5 GB)
mmproj-vlm-v2-r3-f16.gguf — vision projector for r3 (839 MB)
cranebear-extraction-presence.gbnf — grammar
Modelfile.vlm-v2-r2, Modelfile.vlm-v2-r3 — Ollama Modelfiles (SYSTEM block = the prompt)
photo_addendum.py — the photo paragraph, with its SHA
evals/ — the raw eval printouts behind every number above
SHA256SUMS

Downloads last month: 224

GGUF

Model size

4B params

Architecture

qwen3vl

Hardware compatibility

4-bit

Model tree for ajvikram/cranebear-vlm-4b-gguf

Base model

Qwen/Qwen3-VL-4B-Instruct

Quantized

(109)

this model