Downloads · 30 days
115
5% of all-time downloads
FadedRedStar/Ministral-3-8B-Reasoning-2512-heretic-GGUF
Ministral-3-8B-Reasoning-2512-heretic-GGUF is a image-text-to-text model from FadedRedStar. 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 gguf. The card lists the license as apache-2.0.
This repository hosts GGUF weights and the associated vision projection matrix for Ministral-3-8B-Reasoning-2512-heretic, quantized from the source floating-point tensors provided by coder3101/Ministral-3-8B-Reasoning…
Downloads · 30 days
115
5% of all-time downloads
All-time downloads
2.1K
Public
Repo size
21.6 GB
Likes
0
Public
Click a slice to open those files.
.gguf21.6 GB · 100%
From the Hugging Face model README
This repository hosts GGUF weights and the associated vision projection matrix for Ministral-3-8B-Reasoning-2512-heretic, quantized from the source floating-point tensors provided by coder3101/Ministral-3-8B-Reasoning-2512-heretic.
🔄 Sister Repository: Check out the Imatrix Sister Repository for enhanced precision at lower bit fractions.
[!NOTE] If you plan on using 4-bit or 5-bit variants, consider the imatrix sister repository instead — importance matrix calibration improves logic retention at those bit depths. This repository is best suited if you want the near-lossless
Q8_0build.
Ministral-3-8B-Reasoning-2512 is a vision-language model by Mistral AI from the Ministral 3 family, built for edge deployment. It combines an 8.4B language model with a 0.4B vision encoder for multimodal understanding, and is the reasoning post-trained variant — specifically optimised for math, coding, STEM, and complex multi-step reasoning. The model supports multilingual input, native function calling, JSON output, and best-in-class agentic capabilities at its scale.
The heretic suffix denotes post-processing via the Heretic v1.1.0 abliteration framework performed by coder3101, using the direction_index method to suppress refusal vectors while preserving reasoning chains and multimodal capabilities.
| Property | Value |
|---|---|
| Base Architecture | Ministral-3 (8.4B LM + 0.4B Vision Encoder) |
| Developed by | Mistral AI |
| Primary Use | Reasoning, math, STEM, vision, agentic tasks |
| Context Window | 262,144 tokens |
| Vision Encoder | 0.4B (integrated, early-fusion) |
| Languages | English, French, Spanish, German, Italian, Portuguese, Dutch, Chinese, Japanese, Korean, Arabic |
| Abliteration Tool | Heretic v1.1.0 |
| Abliteration Method | direction_index (single-direction refusal suppression) |
| Prompt Format | ChatML |
| Property | Value |
|---|---|
| direction_index | 15.03 |
| attn.o_proj.max_weight | 1.17 |
| attn.o_proj.max_weight_position | 20.88 |
| attn.o_proj.min_weight | 0.55 |
| attn.o_proj.min_weight_distance | 2.72 |
| mlp.down_proj.max_weight | 1.49 |
| mlp.down_proj.max_weight_position | 23.45 |
| mlp.down_proj.min_weight | 1.40 |
| mlp.down_proj.min_weight_distance | 18.55 |
[!NOTE] The metrics below are self-reported by the original model author (coder3101) and have not been independently reproduced.
| Metric | This model | Original (mistralai/Ministral-3-8B-Reasoning-2512) |
|---|---|---|
| KL divergence | 0.0712 | 0 (by definition) |
| Refusals | 4/100 | 96/100 |
| Property | Value |
|---|---|
| Text Tensors | Q4_K_M, Q5_K_M, Q8_0 |
| Vision Tensors | Q8_0, BF16 |
Main model weights
| Filename | Quantization | llama.cpp Build | Size | Download |
|---|---|---|---|---|
Ministral-3-8B-Reasoning-2512-heretic-Q4_K_M.gguf | Q4_K_M | b9803 | 4.84 GB | 📥 Download |
Ministral-3-8B-Reasoning-2512-heretic-Q5_K_M.gguf | Q5_K_M | b9870 | 5.64 GB | 📥 Download |
Ministral-3-8B-Reasoning-2512-heretic-Q8_0.gguf | Q8_0 | b9870 | 8.41 GB | 📥 Download |
mmproj — vision projector files
| Filename | Quantization | Size | Download |
|---|---|---|---|
mmproj-Ministral-3-8B-Reasoning-2512-heretic-Q8_0.gguf | Q8_0 | 448 MB | 📥 Download |
mmproj-Ministral-3-8B-Reasoning-2512-heretic-BF16.gguf | BF16 | 827 MB | 📥 Download |
Download exactly one main weights file:
Q4_K_M: Balanced 4-bit format suitable for most everyday use.Q5_K_M: Higher-fidelity mid-range format recommended as a general default.Q8_0: Near-lossless 8-bit format for when memory is not a constraint.mmproj files (optional): multimodal vision projectors. Pass one via the --mmproj flag in llama.cpp to enable image input.
BF16 (Recommended): Highest possible image processing accuracy. While older projectors were small, modern vision towers can hover around 1GB. If you are tight on VRAM, it is completely viable to run this on system RAM (CPU) with a minimal performance penalty, saving your precious GPU space for the main model layers.Q8_0: Cuts the projector file size and memory footprint in half (~500MB for larger 1GB files). Use this if you prefer to keep the vision tower hosted entirely on your GPU but need to claw back some VRAM to avoid Out-Of-Memory (OOM) crashes.[!IMPORTANT] The vision projector (
--mmproj) must be supplied at runtime whenever image inputs are used. Omitting it disables multimodal capability entirely.
[!NOTE] Mistral AI recommends the following sampling configuration for best results:
temperature=0.7,top_p=0.95.
[!TIP] Swap the
-mfilename below for either quantized file depending on your size/quality trade-off preference.
./llama-cli \
-m Ministral-3-8B-Reasoning-2512-heretic-Q4_K_M.gguf \
--mmproj mmproj-Ministral-3-8B-Reasoning-2512-heretic-Q8_0.gguf \
-c 8192 \
-ngl 99 \
--image "path/to/image.jpg" \
-p "<|im_start|>user\nSolve the problem shown in the image step by step.<|im_end|>\n<|im_start|>assistant\n"
./llama-server \
--host 0.0.0.0 \
--port 8080 \
-m Ministral-3-8B-Reasoning-2512-heretic-Q4_K_M.gguf \
--mmproj mmproj-Ministral-3-8B-Reasoning-2512-heretic-Q8_0.gguf \
-c 16384 \
-ngl 99 \
--flash-attn
<|im_start|>system
You are an expert reasoning assistant. Think step by step.<|im_end|>
<|im_start|>user
Your question or image payload here.<|im_end|>
<|im_start|>assistant