Downloads · 30 days
67
3% of all-time downloads
PishangShedappp/gemma-4-31B-it-claude-opus-4.8-max-thinking-mxfp8-mlx
gemma-4-31B-it-claude-opus-4.8-max-thinking-mxfp8-mlx is a image-text-to-text model from PishangShedappp. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as gemma.
This model is a highly optimized, locally-trained version of Google's Gemma-4-31B-it, fine-tuned specifically to emulate the advanced step-by-step reasoning and "Max Thinking" cognitive architecture of Claude Opus.
Downloads · 30 days
67
3% of all-time downloads
All-time downloads
2K
Public
Parameters
30.7B
31.7 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors31.7 GB · 100%
How the weights are stored.
U3230.7B · 100%
From the Hugging Face model README
This model is a highly optimized, locally-trained version of Google's Gemma-4-31B-it, fine-tuned specifically to emulate the advanced step-by-step reasoning and "Max Thinking" cognitive architecture of Claude Opus.
It was fine-tuned entirely on Apple Silicon utilizing the Apple MLX framework and is fused natively for macOS environments.
google/gemma-4-31B-it11-47/claude_opus_4.8_max_thinking_5k_v2mlx_lm)mxfp4)This model was trained using a custom LoRA adapter focusing purely on the output reasoning structures (--mask-prompt enabled) to prevent prompt-memorization and ensure robust zero-shot logical deduction.
This model is fully fused and ready for immediate deployment on Macs using the MLX framework.
Make sure you have the MLX ecosystem installed:
pip install mlx-lm
You can chat with the model interactively straight from your terminal:
mlx_lm.chat --model PishangShedappp/gemma-4-31B-it-claude-opus-4.8-max-thinking-mxfp8-mlx
If you want to integrate this reasoning model into your own macOS applications or backend scripts:
from mlx_lm import load, generate
# Load the model and tokenizer
model, tokenizer = load("PishangShedappp/gemma-4-31B-it-claude-opus-4.8-max-thinking-mxfp8-mlx")
# Format your prompt using the Gemma chat template
messages = [{"role": "user", "content": "Explain why quantum computing is different from classical computing step-by-step."}]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
# Generate the reasoning output
response = generate(
model,
tokenizer,
prompt=prompt,
max_tokens=1000,
verbose=True
)
You can expose this model as a local, OpenAI-compatible API endpoint:
mlx_lm.server --model PishangShedappp/gemma-4-31B-it-claude-opus-4.8-max-thinking-mxfp8-mlx --port 8080
The model was fine-tuned with the following hyper-parameters using mlx_lm.lora:
2e-5Because this is a 31B parameter model compressed to mxfp8, it requires a Mac with at least 48GB of Unified Memory to run comfortably during inference, and 64GB of Unified Memory for high-context workloads or local re-training.