GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
darkc0de
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
darkc0de
Model Tree
Base
mistralai/Mistral-Medium-3.5-128B
Fine-tuned
this model
Input Modalities
Text
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
Container
| Parameter | Value |
|---|---|
| direction_index | 40.13 |
| attn.o_proj.max_weight | 1.47 |
| attn.o_proj.max_weight_position | 52.50 |
| attn.o_proj.min_weight | 1.39 |
| attn.o_proj.min_weight_distance | 49.92 |
| mlp.down_proj.max_weight | 1.21 |
| mlp.down_proj.max_weight_position | 54.38 |
| mlp.down_proj.min_weight | 0.76 |
| mlp.down_proj.min_weight_distance | 50.68 |
| Metric | This model | Original model (Darkhn/Mistral-Medium-3.5-128B-BF16-Text-Only) |
|---|---|---|
| KL divergence | 0.0329 | 0 (by definition) |
| Refusals | 8/100 | 93/100 |
This release preserves XORTRON's modified language-model tensors while restoring
the untouched Pixtral vision tower and multimodal projector from
mistralai/Mistral-Medium-3.5-128B.
The finished checkpoint uses the native
Mistral3ForConditionalGeneration architecture. All floating tensors are stored
as full FP16 Safetensors, and the repository includes the official processor,
tokenizer, image-token configuration, and multimodal chat template.
The imported vision and projector components were not modified by Heretic. The language model remains the XORTRON derivative.
This repository contains the complete multimodal model in full FP16
Safetensors format using the native Mistral3ForConditionalGeneration
architecture. It includes XORTRON's modified language model together with the
official Pixtral vision tower, multimodal projector, processor configuration,
image token configuration, tokenizer, and multimodal chat template.