Image-Text-to-Text
MLX
Safetensors
inkling2_loop
apple-silicon
Mixture of Experts
dspark
speculative-decoding
conversational
4-bit precision
Instructions to use netprojects/Inkling-2-Mini-MLX-4-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use netprojects/Inkling-2-Mini-MLX-4-8bit with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("netprojects/Inkling-2-Mini-MLX-4-8bit") config = load_config("netprojects/Inkling-2-Mini-MLX-4-8bit") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use netprojects/Inkling-2-Mini-MLX-4-8bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "netprojects/Inkling-2-Mini-MLX-4-8bit"
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "netprojects/Inkling-2-Mini-MLX-4-8bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent
How to use netprojects/Inkling-2-Mini-MLX-4-8bit with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "netprojects/Inkling-2-Mini-MLX-4-8bit"
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 netprojects/Inkling-2-Mini-MLX-4-8bit
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use netprojects/Inkling-2-Mini-MLX-4-8bit with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "netprojects/Inkling-2-Mini-MLX-4-8bit"
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 "netprojects/Inkling-2-Mini-MLX-4-8bit" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Card: title mentions the bundled DSpark speculative decoding
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ tags:
|
|
| 14 |
- speculative-decoding
|
| 15 |
---
|
| 16 |
|
| 17 |
-
# Inkling 2 Mini for Apple Silicon (MLX, 4/8-bit, lossless)
|
| 18 |
|
| 19 |
[thinkingmachines/Inkling-2-Mini](https://huggingface.co/thinkingmachines/Inkling-2-Mini) (revision `6e7c824`) for MLX on
|
| 20 |
Apple Silicon, with its DSpark speculative-decoding draft bundled (`mtp.safetensors`) and its vision encoder included.
|
|
@@ -28,6 +28,7 @@ Inkling 2 Mini is Thinking Machines' looped mixture-of-experts model: 26.4B para
|
|
| 28 |
| Build | Size | Same next token as Thinking Machines' code | KL vs their code | GSM8K (50 questions) | Peak memory, 8K-token prompt |
|
| 29 |
|---|---|---|---|---|---|
|
| 30 |
| [netprojects/Inkling-2-Mini-MLX-4-8bit](https://huggingface.co/netprojects/Inkling-2-Mini-MLX-4-8bit) (recommended) | 20.2 GB + 0.64 GB draft | 98.6% | 0.0018 | 47/50 | 27.8 GB |
|
|
|
|
| 31 |
|
| 32 |
"Thinking Machines' code" is their Transformers implementation of Inkling 2 Mini, run on the released weights; the
|
| 33 |
columns are explained under "What was checked".
|
|
@@ -100,7 +101,7 @@ harnesses and settings; a selection of their table):
|
|
| 100 |
|
| 101 |
## What was checked
|
| 102 |
|
| 103 |
-
On a MacBook Pro M5 Max (128 GB),
|
| 104 |
|
| 105 |
- **Against Thinking Machines' code.** Their Transformers implementation (pull request #51050) ran on the CPU with the
|
| 106 |
released weights, on 12 short chat texts (488 answer positions). This build gave the same next token at
|
|
|
|
| 14 |
- speculative-decoding
|
| 15 |
---
|
| 16 |
|
| 17 |
+
# Inkling 2 Mini for Apple Silicon (MLX, 4/8-bit, lossless, with DSpark speculative decoding)
|
| 18 |
|
| 19 |
[thinkingmachines/Inkling-2-Mini](https://huggingface.co/thinkingmachines/Inkling-2-Mini) (revision `6e7c824`) for MLX on
|
| 20 |
Apple Silicon, with its DSpark speculative-decoding draft bundled (`mtp.safetensors`) and its vision encoder included.
|
|
|
|
| 28 |
| Build | Size | Same next token as Thinking Machines' code | KL vs their code | GSM8K (50 questions) | Peak memory, 8K-token prompt |
|
| 29 |
|---|---|---|---|---|---|
|
| 30 |
| [netprojects/Inkling-2-Mini-MLX-4-8bit](https://huggingface.co/netprojects/Inkling-2-Mini-MLX-4-8bit) (recommended) | 20.2 GB + 0.64 GB draft | 98.6% | 0.0018 | 47/50 | 27.8 GB |
|
| 31 |
+
| [netprojects/Inkling-2-Mini-MLX-3bit](https://huggingface.co/netprojects/Inkling-2-Mini-MLX-3bit) | 15.5 GB + 0.64 GB draft | 94.9% | 0.0430 | 49/50 | 21.8 GB |
|
| 32 |
|
| 33 |
"Thinking Machines' code" is their Transformers implementation of Inkling 2 Mini, run on the released weights; the
|
| 34 |
columns are explained under "What was checked".
|
|
|
|
| 101 |
|
| 102 |
## What was checked
|
| 103 |
|
| 104 |
+
On a MacBook Pro M5 Max (128 GB), 21 November 2026, with MLX 0.32.4 and [inkling2-mlx](https://github.com/internet-projects/inkling2-mlx) v0.1.0.
|
| 105 |
|
| 106 |
- **Against Thinking Machines' code.** Their Transformers implementation (pull request #51050) ran on the CPU with the
|
| 107 |
released weights, on 12 short chat texts (488 answer positions). This build gave the same next token at
|