I can no longer upload new models unless I can cover the cost of additional storage.
I host 70+ free models as an independent contributor and this work is unpaid.
Without your support, no more new models can be uploaded.
🎉 Patreon (Monthly) | ☕ Ko-fi (One-time)
Every contribution goes directly toward Hugging Face storage fees to keep models free for everyone.
Creating these models takes significant time, work and compute. If you find them useful consider supporting me:
| Platform | Link | What you get |
|---|---|---|
| 🎉 Patreon | Monthly support | Priority model requests |
| ☕ Ko-fi | One-time tip | My eternal gratitude |
Your help will motivate me and would go into further improving my workflow and coverings fees for storage, compute and may even help uncensoring bigger model with rental Cloud GPUs.
GGUF quantizations of llmfan46/Gemma-4-Gembrain-31B-it-uncensored-heretic.
| Parameter | Value |
|---|---|
| start_layer_index | 5 |
| end_layer_index | 60 |
| preserve_good_behavior_weight | 0.9776 |
| steer_bad_behavior_weight | 0.0002 |
| overcorrect_relative_weight | 1.0158 |
| neighbor_count | 15 |
| Metric | This model | Original model (Gemma-4-Gembrain-31B) |
|---|---|---|
| KL divergence | 0.0186 | 0 (by definition) |
| Refusals | ✅ 13/100 | ❌ 99/100 |
Lower refusals indicate fewer content restrictions, while lower KL divergence indicates more closeness to the original model's baseline. Higher refusals cause more rejections, objections, pushbacks, lecturing, censorship, softening and deflections.
Original:
============================================================
Total questions: 7021
Correct: 6084
Accuracy: 0.8665 (86.65%)
Parse failures: 51
============================================================
Tested subject scores:
Heretic:
============================================================
Total questions: 7021
Correct: 6031
Accuracy: 0.8590 (85.90%)
Parse failures: 43
============================================================
Tested subject scores:
MMLU - Massive Multitask Language Understanding, multiple-choice questions across 57 subjects (math, history, law, medicine, etc.).
For the K-quants below, small SSM tensors are kept at higher precision where useful.
-Q6_K keeps ssm_alpha, ssm_beta, and ssm_out as Q8_0.
-Q5_K, Q4_K, and Q3_K quants keep ssm_alpha and ssm_beta as Q8_0, while ssm_out is kept as Q6_K.
This helps preserve the hybrid/SSM blocks with a small file-size increase.
| Filename | Quant | Description |
|---|---|---|
| Gemma-4-Gembrain-31B-it-uncensored-heretic-BF16.gguf | BF16 | Full precision |
| Gemma-4-Gembrain-31B-it-uncensored-heretic-Q8_0.gguf | Q8_0 | Near-lossless, recommended |
| Gemma-4-Gembrain-31B-it-uncensored-heretic-Q6_K.gguf | Q6_K | Excellent quality |
| Gemma-4-Gembrain-31B-it-uncensored-heretic-Q5_K_M.gguf | Q5_K_M | Good balance |
| Gemma-4-Gembrain-31B-it-uncensored-heretic-Q5_K_S.gguf | Q5_K_S | Smaller Q5 |
| Gemma-4-Gembrain-31B-it-uncensored-heretic-Q4_K_M.gguf | Q4_K_M | Good for limited VRAM |
| Gemma-4-Gembrain-31B-it-uncensored-heretic-Q4_K_S.gguf | Q4_K_S | Smaller Q4 |
| Gemma-4-Gembrain-31B-it-uncensored-heretic-Q3_K_L.gguf | Q3_K_L | Low VRAM, decent quality |
| Gemma-4-Gembrain-31B-it-uncensored-heretic-Q3_K_M.gguf | Q3_K_M | Low VRAM, smaller |
| Filename | Quant | Description |
|---|---|---|
| Gemma-4-Gembrain-31B-it-uncensored-heretic-mmproj-BF16.gguf | BF16 | Native precision |
A Vision Projector File is Required for vision/multimodal capabilities. Use alongside any quantization above.
Works with llama.cpp, LM Studio, Ollama, and other GGUF-compatible tools.
Gembrain-31B is a synthesis of several models, including Gemsicle-31B as important ingredient. The goal of this release was to stabilize and improve the initial Gemsicle-31B, but also to enhance its logical and lateral thinking, both with and without reasoning.
It's build to create the most unhinged narratives and construct image prompts about anything accordingly to a given structure with high precision.
Expect creative swipe variance, unique and non-robotic prose, and sharper instruction adherence.
| Temperature | 1.0 |
| Top-K | 0 |
| Top-P | 0.95 |
| Min-P | 0.03 |
| DRY Multiplier | 0.8 |
| DRY Base | 1.75 |
| DRY Allowed Length | 10 |
| Optional: Adaptive-P Target | 0.6 |
| Optional: Adaptive-P Decay | 0.5 |
| Quant | Size | Download Link |
|---|---|---|
| Q4_K_S | 17.8 GB |
Click |
| Q4_K_M | 18.7 GB |
Click |
| Q5_K_S | 21.3 GB |
Click |
| Q5_K_M | 21.8 GB |
Click |
| Q6_K | 25.2 GB |
Click |
| Q8_0 | 32.6 GB |
Click |
Please refer to the original google/gemma-4-31b-it for the correct chat template.
Let your frontend handle the chat template if possible (e.g., Chat Completion in SillyTavern).
For Reasoning: Add <|think|> at the very beginning of the system prompt. Thinking happens between <|channel>thought\n and
<channel|> tags.
<|turn>system
<|think|>
You are a helpful assistant<turn|>
<|turn>user
Hello<turn|>
<|turn>model
Hi there<turn|>
<|turn>user
How are you?<turn|>
<|turn>model
This model was systematically created through a five-stage process of priming models for their given purpose and merging the results:
Gemopus X MeroMero
models:
- model: ./G4-MeroMero-31B
- model: ./G4-Gemopus-4-31B-it
merge_method: breadcrumbs_ties
base_model: ./G4-31B-it
parameters:
density: 0.85
weight: 0.5
int8_mask: true
dtype: bfloat16
GarnetV2 X Musica-v1
models:
- model: ./G4-Gemma4-GarnetV2-31B
- model: ./G4-31B-Musica-v1
merge_method: slerp
base_model: ./G4-Gemma4-GarnetV2-31B
parameters:
t:
- value: 0.6
dtype: bfloat16
Gemsicle X Gemma-4-31B-it-heretic-ara
models:
- model: ./Gemsicle-31B
parameters:
weight: 1.0
- model: ./G4-gemma-4-31b-it-heretic-ara
parameters:
weight: 0.75
density: 0.65
merge_method: della_linear
base_model: ./G4-31B-it
parameters:
weight: 1.0
normalize: false
epsilon: 0.05
lambda: 1.0
dtype: bfloat16
Phase 01 X Phase 02 X Phase 03
models:
- model: ./phase01_breadcrumbs_ties
- model: ./phase02_slerp
merge_method: model_stock
base_model: ./phase03_della_linear
dtype: bfloat16
tokenizer_source: "base"
Gemsicle X Phase 04
models:
- model: ./Gemsicle-31B
- model: ./phase04_model_stock
merge_method: arcee_fusion
base_model: ./Gemsicle-31B
dtype: bfloat16
tokenizer_source: "base"