Downloads · 30 days
5K
32% of all-time downloads
anik-jha/Qwen3.6-35B-A3B-coding-reap50-GGUF
Qwen3.6-35B-A3B-coding-reap50-GGUF is a machine learning model from anik-jha. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for llama.cpp. The card lists the license as apache-2.0.
Paper: Half the Experts, All the Code, accepted at the COLM 2026 Workshop on Efficient Reasoning (October 9, 2026, San Francisco; non-archival). Preprint: arXiv:2607.16721 · Workshop version: OpenReview
Downloads · 30 days
5K
32% of all-time downloads
All-time downloads
15.4K
Public
Repo size
24.6 GB
Likes
17
Trending 2
Click a slice to open those files.
.gguf24.6 GB · 100%
From the Hugging Face model README
Paper: Half the Experts, All the Code, accepted at the COLM 2026 Workshop on Efficient Reasoning (October 9, 2026, San Francisco; non-archival). Preprint: arXiv:2607.16721 · Workshop version: OpenReview
Qwen3.6-35B-A3B with half of its experts removed (128 of 256 per layer, REAP scoring on a coding-heavy calibration mix), quantized with an importance matrix. This is the main artifact of the paper Half the Experts, All the Code (arXiv:2607.16721): a 19B-parameter coding specialist that fits where the full model does not.
Why you might want it: at the same memory budget, these beat 2-bit quantization of the full model on HumanEval+.
| file | size | HumanEval+ | MBPP+ |
|---|---|---|---|
| Q4_K_M (imatrix) | 11.4 GB | 0.902 | 0.720 |
| Q5_K_M (imatrix) | 13.3 GB | 0.915 | 0.749 |
| full model, IQ2_M (for comparison, not included) | 13.0 GB | 0.896 | 0.730 |
| full model, Q8 (for comparison, not included) | 38 GB | 0.890 | 0.772 |
All numbers are greedy pass@1 via EvalPlus against llama.cpp, reasoning off. The trade is real: general (non-coding) perplexity roughly doubles. This is a coding specialist, not a general assistant - don't deploy it as one.
Made with moep; the exact expert
selection JSON is in that repo under artifacts/selections/, so you can
reproduce the surgery from the base checkpoint. Runs anywhere llama.cpp
runs.
Derivative of Qwen3.6-35B-A3B, Apache-2.0, upstream notice retained.
@misc{jha2026halfexperts,
title = {Half the Experts, All the Code: One-Shot Domain Pruning of Mixture-of-Experts LLMs for Coding},
author = {Jha, Anik},
year = {2026},
eprint = {2607.16721},
archivePrefix = {arXiv},
primaryClass = {cs.LG},
note = {Accepted at the COLM 2026 Workshop on Efficient Reasoning},
url = {https://arxiv.org/abs/2607.16721}
}