prithivMLmods/Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0-GGUF overview
Qwen3.5 2B Opus Distilled Heretic Thinking Multistage SFT v1.0 GGUF Qwen3.5 2B Opus Distilled Heretic Thinking Multistage SFT v1.0 https://huggingface.co/prith…
Runs locally from ~347.8 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.BF16.gguf | GGUF | GGUF | 3.52 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.F16.gguf | GGUF | GGUF | 3.52 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.Q3_K_L.gguf | GGUF | GGUF | 1.08 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.Q3_K_M.gguf | GGUF | GGUF | 1.02 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.Q3_K_S.gguf | GGUF | GGUF | 972.9 MB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.Q4_K_M.gguf | GGUF | GGUF | 1.19 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.Q4_K_S.gguf | GGUF | GGUF | 1.13 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.Q5_K_M.gguf | GGUF | GGUF | 1.31 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.Q5_K_S.gguf | GGUF | GGUF | 1.28 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.Q6_K.gguf | GGUF | GGUF | 1.45 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.Q8_0.gguf | GGUF | GGUF | 1.87 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.mmproj-bf16.gguf | GGUF | BF16 | 640.3 MB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.mmproj-f16.gguf | GGUF | F16 | 640.3 MB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.mmproj-q8_0.gguf | GGUF | Q8_0 | 347.8 MB | Download |
Model Details
| Model ID | prithivMLmods/Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0-GGUF |
|---|---|
| Author | prithivMLmods |
| Pipeline | image-text-to-text |
| License | apache-2.0 |
| Base model | prithivMLmods/Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0 |
| Last modified | 2026-08-07T20:08:35.000Z |
Model README
---
license: apache-2.0
base_model:
- prithivMLmods/Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0
tags:
- text-generation-inference
- llama-cpp
- 32k-context
- local-inference
- qwen3.5
- 9b
- opus-4.7
- sft
- multi-stage-training
- multitask
- reasoning
- logical-reasoning
- problem-solving
- math
- long-context
- community-model
- oss
- text-generation
language:
- en
pipeline_tag: image-text-to-text
library_name: transformers
---
Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0-GGUF
> Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0 is a reasoning-capable 2B-parameter language model built on top of Qwen/Qwen3.5-2B. The model was trained using a multi-stage supervised fine-tuning (SFT) pipeline on approximately 6,000 coding and STEM-focused Opus reasoning traces, along with additional high-quality reasoning traces, to improve long-form reasoning, coding, mathematical problem solving, scientific analysis, and instruction-following capabilities.
> [!NOTE]
> This model is an experimental release and may generate unexpected behaviors or reasoning artifacts in certain scenarios.
Model Files
File Name | Quant Type | File Size | File Link |
|-----------|------------|-----------|-----------|
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.BF16.gguf | BF16 | 3.78 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.F16.gguf | F16 | 3.78 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.Q3_K_L.gguf | Q3_K_L | 1.16 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.Q3_K_M.gguf | Q3_K_M | 1.1 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.Q3_K_S.gguf | Q3_K_S | 1.02 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.Q4_K_M.gguf | Q4_K_M | 1.27 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.Q4_K_S.gguf | Q4_K_S | 1.21 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.Q5_K_M.gguf | Q5_K_M | 1.41 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.Q5_K_S.gguf | Q5_K_S | 1.37 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.Q6_K.gguf | Q6_K | 1.56 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.Q8_0.gguf | Q8_0 | 2.01 GB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.mmproj-bf16.gguf | mmproj-bf16 | 671 MB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.mmproj-f16.gguf | mmproj-f16 | 671 MB | Download |
| Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0.mmproj-q8_0.gguf | mmproj-q8_0 | 365 MB | Download |
llama.cpp
LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp
Run prithivMLmods/Qwen3.5-2B-Opus-Distilled-Heretic-Thinking-Multistage-SFT-v1.0-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models