nikhil-singh-iphtech/Qwen3-0.6B-mEinstein_v3-GGUF overview
Qwen3 0.6B mEinstein GGUF Fine tuned version of Qwen/Qwen3 0.6B https://huggingface.co/Qwen/Qwen3 0.6B on the mEinstein personal AI assistant dataset. Availabl…
Runs locally from ~378.3 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | nikhil-singh-iphtech/Qwen3-0.6B-mEinstein_v3-GGUF |
|---|---|
| Author | nikhil-singh-iphtech |
| Pipeline | — |
| License | apache-2.0 |
| Base model | Qwen/Qwen3-0.6B |
| Last modified | 2026-06-18T09:21:50.000Z |
Model README
---
license: apache-2.0
base_model: Qwen/Qwen3-0.6B
tags:
- qwen
- gguf
- quantized
- medical
- fine-tuned
language:
- en
---
Qwen3-0.6B mEinstein GGUF
Fine-tuned version of Qwen/Qwen3-0.6B
on the mEinstein personal AI assistant dataset.
Available Quantizations
| File | Format | Size | Use case |
|------|--------|------|----------|
| Qwen_mEinstein_F16.gguf | F16 | ~1.2 GB | Highest quality |
| Qwen_mEinstein_Q8_0.gguf | Q8_0 | ~0.6 GB | Balanced |
| Qwen_mEinstein_Q4_K_M.gguf| Q4_K_M | ~0.4 GB | Fastest / lightest |
How to Run
./llama-cli -m Qwen_mEinstein_Q4_K_M.gguf -p "Who am I?" -n 256Training Details
- Base model: Qwen/Qwen3-0.6B
- Method: QLoRA (4-bit) + SFT
- LoRA target modules: q_proj, k_proj, v_proj, o_proj
- Dataset: mEinstein personal assistant dataset
Run nikhil-singh-iphtech/Qwen3-0.6B-mEinstein_v3-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models