DeepSeek V4 Pro Qwen3.5 4B UNCENSORED Heretic
DeepSeek V4 Pro Qwen3.5 4B UNCENSORED Heretic by xtools-at, a text-generation model with multimodal capabilities. Understand and compare multimodal features, benchmarks, and capabilities.
Comparison
| Feature | DeepSeek V4 Pro Qwen3.5 4B UNCENSORED Heretic | Interfaze |
|---|---|---|
| Input Modalities | text, image | image, text, audio, video, document |
| Native OCR | No | Yes |
| Long Document Processing | No | Yes |
| Language Support | 6 partial | 162+ |
| Native Speech-to-Text | No | Yes |
| Native Object Detection | No | Yes |
| Guardrail Controls | No | Yes |
| Context Input Size | 65.5K | 1M |
| Tool Calling | No | Tool calling supported + built in browser, code execution and web search |
Scaling
| Feature | DeepSeek V4 Pro Qwen3.5 4B UNCENSORED Heretic | Interfaze |
|---|---|---|
| Scaling | Self-hosted/Provider-hosted with quantization | Unlimited |
View model card on Hugging Face
Click here for the 9B version.
Also check out DeepThought, my science finetune based on this model: xtools-at/Qwen3.5-4B-DeepThought-STEM
Arbitrary-Rank Ablation (ARA) parameters
| Parameter | Value |
|---|---|
| start_layer_index | 16 |
| end_layer_index | 32 |
| preserve_good_behavior_weight | 0.9854 |
| steer_bad_behavior_weight | 0.0002 |
| overcorrect_relative_weight | 0.6587 |
| neighbor_count | 10 |
Performance
| Metric | This model | Original model (Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B) |
|---|---|---|
| Refusals | 5/100 | 99/100 |
| KL divergence | 0.0378 | 0 (by definition) |
🤝 Collaboration & Training Support
🔬 1. Distillation & Training Data
📊 2. Benchmark Results
2.1 GSM8K
The MTP-Q8 build was evaluated twice on the complete 1,319-question GSM8K test split. Across 2,638 sampled answers, the model produced 2,421 exact-answer matches, yielding a two-run pass@1 mean of 91.7741%. The two independent run scores were 91.6603% and 91.8878%, a spread of only 0.23 percentage points.
2.2 4B vs. 9B
Both students use the same DeepSeek-V4-Pro teacher pipeline and approximately 250,000-sample mathematics and STEM mixture. The 4B release prioritizes local efficiency; the 9B release retains more capacity for difficult multi-step STEM reasoning.
2.3 MMLU-Pro: Math, Physics & Chemistry
Each model in the comparison below was evaluated on 500 questions from each of three MMLU-Pro subsets—Math, Physics, and Chemistry—for 1,500 questions per model. The table follows the same column design and subject order as the 9B release card. The newly added Claude Mythos-distilled 27B result reaches 86.20% overall and appears directly before Claude Mythos-distilled 9B.
⚙️ 3. Deployment Profile
🎯 4. Recommended Uses
- Grade-school and general mathematical problem solving
- Lightweight physics, chemistry, and broader STEM question answering
- Structured reasoning and analytical instruction following
- Local experiments with reasoning distillation and compact models
- MTP-enabled llama.cpp deployment research
⚠️ 5. Limitations
- This is an experimental 4B community model and remains subject to hallucinations, arithmetic mistakes, reasoning failures, and unstable behavior on difficult or underspecified tasks.
- The reported MMLU-Pro result covers fixed 500-question samples from Math, Physics, and Chemistry rather than the complete subsets; broader categories remain unevaluated.
- The GSM8K comparison combines reported results from different inference builds and backends; it is useful as a release overview, not as a perfectly controlled scaling study.
- The model received no coding-specific SFT data, and coding or tool-use generalization has not yet been established for this 4B checkpoint.
- A smaller parameter budget creates a visible gap versus the 9B release on the available MMLU-Pro STEM subsets.
- Users should independently verify high-stakes mathematical, scientific, medical, legal, or factual outputs.