Capabilities
Minimum system memory
Tags
Last updated
Updated 12 days agobyREADME
Parameters
Custom configuration options included with this model
Sources
The underlying model files this model uses
Based on
MLX
Text ยท Vision ยท Thinking ยท Tool Calling
Converted from mistralai/Mistral-Medium-3.5-128B (FP8, 133.6 GB) to MLX 4-bit for Apple Silicon.
reasoning_effort to "high" for deep reasoning with [THINK]...[/THINK] blocks[TOOL_CALLS] tokensFrom Mistral AI and Unsloth recommendations.
reasoning_effort="high")For complex prompts, coding, research, math, and agentic usage:
| Parameter | Value |
|---|---|
| temperature | 0.7 |
| top_p | 0.95 |
| top_k | 20 |
reasoning_effort="none")For fast replies, chat, extraction, and simple instructions:
| Parameter | Value |
|---|---|
| temperature | 0.0โ0.7 |
| top_p | 0.8 |
Keep repetition and presence penalties disabled (1.0) unless you see looping.
| Role | Author |
|---|---|
| Original model | Mistral AI |
| MLX conversion | froggeric |
Modified MIT โ revenue cap $20M/month. See full license.