Instructions to use evalengine/unbound-e2b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use evalengine/unbound-e2b-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="evalengine/unbound-e2b-gguf",
	filename="mmproj-unbound-e2b.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 evalengine/unbound-e2b-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf evalengine/unbound-e2b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf evalengine/unbound-e2b-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf evalengine/unbound-e2b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf evalengine/unbound-e2b-gguf: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 evalengine/unbound-e2b-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf evalengine/unbound-e2b-gguf: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 evalengine/unbound-e2b-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf evalengine/unbound-e2b-gguf:Q4_K_M

Use Docker

docker model run hf.co/evalengine/unbound-e2b-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use evalengine/unbound-e2b-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "evalengine/unbound-e2b-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": "evalengine/unbound-e2b-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/evalengine/unbound-e2b-gguf:Q4_K_M

Ollama
How to use evalengine/unbound-e2b-gguf with Ollama:
```
ollama run hf.co/evalengine/unbound-e2b-gguf:Q4_K_M
```

Unsloth Studio new

How to use evalengine/unbound-e2b-gguf 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 evalengine/unbound-e2b-gguf 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 evalengine/unbound-e2b-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for evalengine/unbound-e2b-gguf to start chatting

Pi new

How to use evalengine/unbound-e2b-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf evalengine/unbound-e2b-gguf: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": "evalengine/unbound-e2b-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use evalengine/unbound-e2b-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf evalengine/unbound-e2b-gguf: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 evalengine/unbound-e2b-gguf:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use evalengine/unbound-e2b-gguf with Docker Model Runner:
```
docker model run hf.co/evalengine/unbound-e2b-gguf:Q4_K_M
```

Lemonade

How to use evalengine/unbound-e2b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull evalengine/unbound-e2b-gguf:Q4_K_M

Run and chat with the model

lemonade run user.unbound-e2b-gguf-Q4_K_M

List all available models

lemonade list

johnsonchromia commited on 2 days ago

Commit

3301a7d

verified ·

1 Parent(s): 6975824

README: 3-quant lineup, split-file UX, wllama browser support

Browse files

Files changed (1) hide show

README.md +35 -10

README.md CHANGED Viewed

@@ -24,17 +24,23 @@ pipeline_tag: text-generation
 > use it and for complying with all applicable laws.
 GGUF quantizations of [`evalengine/unbound-e2b`](https://huggingface.co/evalengine/unbound-e2b)
-for on-device deployment via Ollama, llama.cpp, LM Studio, and similar runtimes.
 Built by [Chromia](https://x.com/Chromia) and [Eval Engine](https://x.com/eval_engine).
 ## Available quants
-| File | Size | Notes |
-|---|---|---|
-| `unbound-e2b-Q4_K_M.gguf` | 3.2 GB | Recommended phone-deployable build |
-More quants (Q5_K_M, Q8_0, etc.) may be added on request.
 ## Recommended sampling
@@ -51,7 +57,7 @@ through.
 ## Default sampling (Ollama)
-When you `ollama pull hf.co/evalengine/unbound-e2b-gguf`, the bundled
 `Modelfile` sets these defaults, tuned for factual recall:
 - `temperature = 0.6` (lower than Gemma's training default of 1.0 — keeps
@@ -63,7 +69,7 @@ When you `ollama pull hf.co/evalengine/unbound-e2b-gguf`, the bundled
 **To override per-session in Ollama:**
 ```
-ollama run hf.co/evalengine/unbound-e2b-gguf
 >>> /set parameter temperature 1.0   # creative / open-ended
 >>> /set parameter temperature 0.3   # max factual / brand questions
 ```
@@ -74,20 +80,39 @@ include the SYSTEM line from the `Modelfile` as your `--system` argument.
 ## Run with Ollama
 ```bash
-ollama pull hf.co/evalengine/unbound-e2b-gguf
-ollama run  hf.co/evalengine/unbound-e2b-gguf
 ```
 ## Run with llama.cpp
 ```bash
-./llama-cli -m unbound-e2b-Q4_K_M.gguf -p "your prompt"
 ```
 ## About the base
 See [`evalengine/unbound-e2b`](https://huggingface.co/evalengine/unbound-e2b)
 for the full model card, benchmarks, intended use, and the merged HF weights.
 ## Acknowledgements
 - Fine-tuned with [Unsloth](https://github.com/unslothai/unsloth) + Huggingface's [TRL](https://github.com/huggingface/trl).

 > use it and for complying with all applicable laws.
 GGUF quantizations of [`evalengine/unbound-e2b`](https://huggingface.co/evalengine/unbound-e2b)
+for on-device deployment via Ollama, llama.cpp, LM Studio, [wllama](https://github.com/ngxson/wllama)
+(in-browser), and similar runtimes.
 Built by [Chromia](https://x.com/Chromia) and [Eval Engine](https://x.com/eval_engine).
 ## Available quants
+All quants ship as **split multi-part GGUFs** (`*-00001-of-0000N.gguf` ...) so
+they work in browsers (wllama's 2 GB ArrayBuffer cap) and let desktop
+runtimes parallel-download chunks. Ollama, llama.cpp, and LM Studio
+auto-stitch on the first part — same UX as a single file.
+| Quant   | Parts | Total  | Largest part | wllama (browser) | Desktop (Ollama/llama.cpp/LM Studio) | Notes |
+|---------|-------|--------|--------------|------------------|--------------------------------------|-------|
+| Q4_K_M  | 3     | 3.2 GB | 1.79 GB      | ✅                | ✅                                    | Recommended on-device default — best size/quality |
+| Q6_K    | 4     | 3.6 GB | 1.79 GB      | ✅                | ✅                                    | Higher fidelity, still browser-safe |
+| Q8_0    | 4     | 4.6 GB | **2.32 GB**  | ❌ (over 2 GB)    | ✅                                    | Highest fidelity; one tensor exceeds the browser ArrayBuffer limit, so desktop runtimes only |
 ## Recommended sampling
 ## Default sampling (Ollama)
+When you `ollama pull hf.co/evalengine/unbound-e2b-GGUF`, the bundled
 `Modelfile` sets these defaults, tuned for factual recall:
 - `temperature = 0.6` (lower than Gemma's training default of 1.0 — keeps
 **To override per-session in Ollama:**
 ```
+ollama run hf.co/evalengine/unbound-e2b-GGUF
 >>> /set parameter temperature 1.0   # creative / open-ended
 >>> /set parameter temperature 0.3   # max factual / brand questions
 ```
 ## Run with Ollama
 ```bash
+ollama pull hf.co/evalengine/unbound-e2b-GGUF
+ollama run  hf.co/evalengine/unbound-e2b-GGUF
 ```
+(Defaults to Q4_K_M. Ollama auto-stitches the split parts on load.)
 ## Run with llama.cpp
 ```bash
+# point at the FIRST part — llama.cpp follows the chain automatically
+./llama-cli -m unbound-e2b-Q4_K_M-00001-of-00003.gguf -p "your prompt"
+```
+## Run in the browser (wllama)
+[wllama](https://github.com/ngxson/wllama) is a WebAssembly port of llama.cpp
+that runs entirely in the browser — no server, no install. Use Q4_K_M or
+Q6_K (Q8_0 has a tensor above the 2 GB ArrayBuffer limit):
+```js
+import { Wllama } from '@wllama/wllama';
+const wllama = new Wllama(/* … */);
+await wllama.loadModelFromHF(
+  'evalengine/unbound-e2b-GGUF',
+  'unbound-e2b-Q4_K_M-00001-of-00003.gguf'  // wllama follows the chain
+);
 ```
 ## About the base
 See [`evalengine/unbound-e2b`](https://huggingface.co/evalengine/unbound-e2b)
 for the full model card, benchmarks, intended use, and the merged HF weights.
 ## Acknowledgements
 - Fine-tuned with [Unsloth](https://github.com/unslothai/unsloth) + Huggingface's [TRL](https://github.com/huggingface/trl).