Instructions to use OculusMindAI/OculusMind-ToolCall-8B-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use OculusMindAI/OculusMind-ToolCall-8B-v1 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 OculusMindAI/OculusMind-ToolCall-8B-v1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf OculusMindAI/OculusMind-ToolCall-8B-v1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf OculusMindAI/OculusMind-ToolCall-8B-v1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf OculusMindAI/OculusMind-ToolCall-8B-v1: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 OculusMindAI/OculusMind-ToolCall-8B-v1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf OculusMindAI/OculusMind-ToolCall-8B-v1: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 OculusMindAI/OculusMind-ToolCall-8B-v1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf OculusMindAI/OculusMind-ToolCall-8B-v1:Q4_K_M

Use Docker

docker model run hf.co/OculusMindAI/OculusMind-ToolCall-8B-v1:Q4_K_M

LM Studio
Jan

vLLM

How to use OculusMindAI/OculusMind-ToolCall-8B-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OculusMindAI/OculusMind-ToolCall-8B-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OculusMindAI/OculusMind-ToolCall-8B-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OculusMindAI/OculusMind-ToolCall-8B-v1:Q4_K_M

Ollama
How to use OculusMindAI/OculusMind-ToolCall-8B-v1 with Ollama:
```
ollama run hf.co/OculusMindAI/OculusMind-ToolCall-8B-v1:Q4_K_M
```
Unsloth Desktop

How to use OculusMindAI/OculusMind-ToolCall-8B-v1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf OculusMindAI/OculusMind-ToolCall-8B-v1: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": "OculusMindAI/OculusMind-ToolCall-8B-v1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use OculusMindAI/OculusMind-ToolCall-8B-v1 with Docker Model Runner:
```
docker model run hf.co/OculusMindAI/OculusMind-ToolCall-8B-v1:Q4_K_M
```

Lemonade

How to use OculusMindAI/OculusMind-ToolCall-8B-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull OculusMindAI/OculusMind-ToolCall-8B-v1:Q4_K_M

Run and chat with the model

lemonade run user.OculusMind-ToolCall-8B-v1-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use OculusMindAI/OculusMind-ToolCall-8B-v1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf OculusMindAI/OculusMind-ToolCall-8B-v1: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 OculusMindAI/OculusMind-ToolCall-8B-v1:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use OculusMindAI/OculusMind-ToolCall-8B-v1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf OculusMindAI/OculusMind-ToolCall-8B-v1: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 "OculusMindAI/OculusMind-ToolCall-8B-v1: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"

OculusMind-AI commited on 10 days ago

Commit

ad3085a

verified ·

1 Parent(s): a94cf40

Successor renamed to OculusMind-ToolCall-8B-v2: new_version, the links under the title, CHANGELOG 1.3

Browse files

Files changed (2) hide show

CHANGELOG.md +12 -0
README.md +3 -3

CHANGELOG.md CHANGED Viewed

@@ -65,6 +65,18 @@ Outstanding before release — the remaining items need an owner decision, and
 ---
 ## [1.2] — 2026-10-07
 Documentation only. **The weights are byte-identical to 1.0.**

 ---
+## [1.3] — 2026-10-08
+Documentation only. **The weights are byte-identical to 1.0.**
+### Successor renamed to OculusMind-ToolCall-8B-v2
+The successor repository is now
+[`OculusMindAI/OculusMind-ToolCall-8B-v2`](https://huggingface.co/OculusMindAI/OculusMind-ToolCall-8B-v2),
+continuing this repository's naming; the model is still called Pico V2. It was
+first published as `OculusMindAI/Pico-V2`, and that address redirects to the new
+one. `new_version` and the links under the title now use the new name.
 ## [1.2] — 2026-10-07
 Documentation only. **The weights are byte-identical to 1.0.**

README.md CHANGED Viewed

@@ -4,7 +4,7 @@ pipeline_tag: text-generation
 license: apache-2.0
 base_model: mistralai/Ministral-3-8B-Instruct-2512-BF16
 base_model_relation: finetune
-new_version: OculusMindAI/Pico-V2
 datasets:
   - Team-ACE/ToolACE
   - interstellarninja/hermes_reasoning_tool_use
@@ -25,7 +25,7 @@ tags:
 *An OculusMind.AI model, fine-tuned from Mistral AI's Ministral-3-8B-Instruct-2512.*
-> **Superseded by [Pico V2](https://huggingface.co/OculusMindAI/Pico-V2)**, the
 > second generation of this series: the same base model, trained only on
 > OculusMind.AI production agent traffic and selected under a tool-call loop
 > gate. Use Pico V2 for new work. This repository stays available with its
@@ -47,7 +47,7 @@ multi-turn tool use, and becomes **less willing to decline** a call than the
 base — both directions are in [§3](#3-primary-evidence--bfcl-v4), in the same
 tables. It did not meet our own internal promotion rule;
 [§7](#7-the-promotion-rule-and-why-this-model-did-not-meet-it) gives that in
-full. Its successor, [Pico V2](https://huggingface.co/OculusMindAI/Pico-V2), is published.
 This card exists so that a business evaluator, or their engineer, can check our

 license: apache-2.0
 base_model: mistralai/Ministral-3-8B-Instruct-2512-BF16
 base_model_relation: finetune
+new_version: OculusMindAI/OculusMind-ToolCall-8B-v2
 datasets:
   - Team-ACE/ToolACE
   - interstellarninja/hermes_reasoning_tool_use
 *An OculusMind.AI model, fine-tuned from Mistral AI's Ministral-3-8B-Instruct-2512.*
+> **Superseded by [OculusMind-ToolCall-8B-v2 ("Pico V2")](https://huggingface.co/OculusMindAI/OculusMind-ToolCall-8B-v2)**, the
 > second generation of this series: the same base model, trained only on
 > OculusMind.AI production agent traffic and selected under a tool-call loop
 > gate. Use Pico V2 for new work. This repository stays available with its
 base — both directions are in [§3](#3-primary-evidence--bfcl-v4), in the same
 tables. It did not meet our own internal promotion rule;
 [§7](#7-the-promotion-rule-and-why-this-model-did-not-meet-it) gives that in
+full. Its successor, [OculusMind-ToolCall-8B-v2 ("Pico V2")](https://huggingface.co/OculusMindAI/OculusMind-ToolCall-8B-v2), is published.
 This card exists so that a business evaluator, or their engineer, can check our