15 Downloads
Capabilities
Minimum system memory
Tags
Last updated
Updated on April 30byREADME
Text · Vision · Thinking · Tool Calling
Converted from mistralai/Mistral-Medium-3.5-128B (FP8, 133.6 GB) to MLX 4-bit for Apple Silicon.
Parameters
Custom configuration options included with this model
Sources
The underlying model files this model uses
reasoning_effort to "high" for deep reasoning with [THINK]...[/THINK] blocks[TOOL_CALLS] tokensFrom Mistral AI and Unsloth recommendations.
For complex prompts, coding, research, math, and agentic usage:
| Parameter | Value |
|---|---|
| temperature | 0.7 |
| top_p | 0.95 |
| top_k | 20 |
For fast replies, chat, extraction, and simple instructions:
| Parameter | Value |
|---|---|
| temperature | 0.0–0.7 |
| 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 — revenue cap $20M/month. See full license.
Based on