Instructions to use Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM")
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("Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM", device_map="auto")

llama-cpp-python

How to use Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM",
	filename="Elbaz-GLM-4.6V-Flash-PRISM-IQ4_XS.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 Settings

llama.cpp

How to use Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM 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 Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM:IQ4_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM:IQ4_XS

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 Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM:IQ4_XS
# Run inference directly in the terminal:
./llama-cli -hf Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM:IQ4_XS

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 Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM:IQ4_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM:IQ4_XS

Use Docker

docker model run hf.co/Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM:IQ4_XS

LM Studio
Jan

vLLM

How to use Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM",
		"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/Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM:IQ4_XS

SGLang

How to use Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM 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 "Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM" \
    --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": "Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM",
		"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 "Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM" \
        --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": "Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM",
		"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 Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM with Ollama:
```
ollama run hf.co/Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM:IQ4_XS
```

Unsloth Studio

How to use Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM 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 Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM 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 Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM to start chatting

How to use Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM:IQ4_XS

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": "Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM:IQ4_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM:IQ4_XS

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 Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM:IQ4_XS

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM:IQ4_XS

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 "Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM:IQ4_XS" \
  --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"

Docker Model Runner
How to use Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM with Docker Model Runner:
```
docker model run hf.co/Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM:IQ4_XS
```

Lemonade

How to use Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM:IQ4_XS

Run and chat with the model

lemonade run user.Elbaz-GLM-4.6V-Flash-PRISM-IQ4_XS

List all available models

lemonade list

error ollama run

by boss003i - opened Dec 12, 2025

Discussion

boss003i

Dec 12, 2025

ollama run hf.co/Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM
Error: 500 Internal Server Error: llama runner process has terminated: exit status

server log
time=2025-12-12T06:14:44.946-05:00 level=INFO source=sched.go:470 msg="Load failed" model=/home/ubuntu/.ollama/models/blobs/sha256-c7427e77baf811bf04d749116b9ffa443ea0f6acfd5d446665ac64f3fe73c9cf error="llama runner process has terminated: exit status 2"
[GIN] 2025/12/12 - 06:14:44 | 500 | 1.424141105s | 127.0.0.1 | POST "/api/generate"

Ex0bit

Owner Dec 15, 2025

@boss003i - Can I trouble you to confirm the machine/specs and ollama version? (ollama --version)

Ex0bit changed discussion status to closed Dec 18, 2025

boss003i

Dec 25, 2025

ollama version is 0.13.5```

`Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes, ID: GPU`

boss003i

Dec 25, 2025

--- vision hparams ---
load_hparams: image_size: 336
load_hparams: patch_size: 14
load_hparams: has_llava_proj: 0
load_hparams: minicpmv_version: 0
load_hparams: n_merge: 2
load_hparams: n_wa_pattern: 0
load_hparams: image_min_pixels: 6272
load_hparams: image_max_pixels: 3211264

load_hparams: model size: 1707.61 MiB
load_hparams: metadata size: 0.06 MiB
clip_init: failed to load model '/home/ubuntu/.ollama/models/blobs/sha256-88b81ee0ca10a823d7c7aa363a4badf80b43f3b76e0914959bdf9928afb206dd': operator(): unable to find tensor mm.model.fc.weight

SIGSEGV: segmentation violation
PC=0x7fa7119527d1 m=5 sigcode=1 addr=0x7fb496b8c1b8
signal arrived during cgo execution

boss003i

Dec 25, 2025

fixed with new pull

Ex0bit

Owner Dec 25, 2025

•

edited Dec 26, 2025

Original vision mmproj was patch fixed prior to official llama.cpp support. Removing the old blobs and re-downloading should do it.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment