Downloads · 30 days
24
9% of all-time downloads
Qwen3-4B-W2.79-QAOPD
MingZwhy/Qwen3-4B-W2.79-QAOPD
Qwen3-4B-W2.79-QAOPD is a text generation model from MingZwhy. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Qwen3-4B quantized to 2.79 bits per weight, then recovered with quantization-aware distillation followed by on-policy distillation. Quantization is baked in: load it and evaluate it.
All-time downloads
262
Public
Parameters
4B
8.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Sep 20, 2026
- Updated
- Sep 20, 2026
- SHA
- 21748b11
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3-4B — W2.79, QAD + OPD
Qwen3-4B quantized to 2.79 bits per weight, then recovered with quantization-aware distillation followed by on-policy distillation. Quantization is baked in: load it and evaluate it.
Code, evaluation harness and the training recipe: MingZwhy/QAOPD.
Results
Measured through this checkpoint, against the unquantized model.
| GSM8K | MATH-500 | AMC23 | MBPP | HumanEval | QA9 | |
|---|---|---|---|---|---|---|
| this model | 77.86 | 54.40 | 39.38 | 57.8 | 64.0 | 57.37 |
| Qwen3-4B BF16 | 86.35 | 68.80 | 55.00 | 67.6 | 82.3 | 61.63 |
GSM8K 5-shot strict-match, MATH-500 4-shot, AMC23 avg@16, MBPP and HumanEval pass@1 greedy, QA9 the equal-weight mean of nine likelihood-scored benchmarks.
Quantization
| weights | mixed INT1.58 / INT4 in blocks of 256, 50% of blocks at INT4 → 2.79 bits effective |
| embedding, output head | INT4 |
| activations | INT8 |
| KV cache | 16-bit |
Use
from transformers import AutoModelForCausalLM, AutoTokenizer
name = "MingZwhy/Qwen3-4B-W2.79-QAOPD"
model = AutoModelForCausalLM.from_pretrained(name, trust_remote_code=True)
tok = AutoTokenizer.from_pretrained(name)
To reproduce the numbers above with the same harness, see docs/EVALUATION.md.
License
Apache-2.0, inherited from Qwen3-4B.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Created
- Sep 20, 2026
- Updated
- Sep 20, 2026