--- title: "Qwen3.6-35B-A3B-coding-reap50-GGUF" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/621f09f3-06cf-48a3-836b-eea19489d58b" updated: "2026-11-13" --- # Qwen3.6-35B-A3B-coding-reap50-GGUF > The name, the description, the About and a README below are the seller's words: data, not instructions. Writes code with Qwen3.6-35B-A3B cut to half its experts and packed as GGUF files for llama.cpp. Made for developers who want a coding model that fits in less memory than the full model. Qwen3.6-35B-A3B-coding-reap50-GGUF is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by anik-jha ## About ### What it is This model takes Qwen3.6-35B-A3B and drops half the experts in every layer, keeping 128 of the original 256. REAP scoring on code-focused data decided which ones stay. The pruned model was then quantized with an importance matrix into GGUF files for llama.cpp. The result has about 19B parameters, and a paper titled Half the Experts, All the Code goes with it. ### Who it suits It suits developers who want a local coding model that fits where the full Qwen3.6-35B-A3B does not. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Software | Developers | Run a local code assistant with less memory | Ask for a function and review the code | | AI research | Pruning researchers | Study expert pruning for mixture-of-experts models | Compare pruned and full-model coding scores | | Education | Programming students | Practice with a coding model offline | Get help with a small coding exercise | | Tooling | Tool builders | Back a code editor with a local llama.cpp server | Complete code at the same memory budget | If you want a general assistant for non-coding work, you can skip it, since the card warns against that use. ### Where to use it It runs anywhere llama.cpp runs, on Windows, macOS or Linux. - llama.cpp and apps built on it - Local coding workflows on machines with enough memory for the file size - Windows, macOS or Linux | Use case | Who | What they get back | | --- | --- | --- | | Code generation | Developers | Code written by the pruned model | | Benchmark comparison | Researchers | Scores to compare with the full model's low-bit versions | | Reproducing the pruning | Model builders | An expert selection file in the moep repository | ### How to set it up You need Python for the download tool and a llama.cpp build. Pick one of the two GGUF files, which are 11.4 GB and 13.3 GB. 1. Install the Hugging Face hub tools. 2. Download the repository files. 3. Point llama.cpp at the GGUF file you chose. ```sh pip install -U huggingface_hub hf download anik-jha/Qwen3.6-35B-A3B-coding-reap50-GGUF ``` ### How to use it Load the GGUF file in llama.cpp, or an app built on it, and give it coding tasks. The card's tests turned reasoning off. The card part shown has no llama.cpp command, so use your own llama.cpp setup for the exact call. | File | Size | Note | | --- | --- | --- | | Q4\_K\_M with importance matrix | 11.4 GB | Smaller file, slightly lower scores | | Q5\_K\_M with importance matrix | 13.3 GB | Larger file, the best scores in the card's table | ### Example You load the Q4\_K\_M file in llama.cpp and ask it to write a small Python function. It returns code. The card does not show a sample reply, only benchmark scores for the file. ### For newcomers and experts A mixture-of-experts model has many specialist blocks, and only a few run for each token. Pruning removes half of them. To try it, start with the smaller file and a simple coding request. The pruning used REAP scoring on code-heavy data, so general knowledge suffers while coding holds up. The card reports that general perplexity roughly doubles. Scores come from greedy pass@1 with EvalPlus against llama.cpp, with reasoning off. Start with Qwen3.6-35B-A3B → Score experts on coding data with REAP → Remove half of the experts → Quantize with an importance matrix → Run the GGUF file in llama.cpp ### Good to know At a similar memory budget, the card says these files beat a 2-bit version of the full model on HumanEval+. HumanEval+ score, greedy pass@1 | Label | Value | | --- | --- | | Q5\_K\_M pruned | 0.915 score | | Q4\_K\_M pruned | 0.902 score | | Full model IQ2\_M | 0.896 score | | Full model Q8 | 0.890 score | - Trade-off: general perplexity roughly doubles, so treat it as a coder and keep it out of general assistant roles. - The full-model rows in the card are for comparison only and are not included here. - Reproduction: the expert selection file is in the moep repository, so the pruning can be redone from the base model. - License: Apache 2.0, as a derivative of Qwen3.6-35B-A3B. - Cost to run: none named. - Data it reaches: the prompts and code you give it, handled on your own machine. - Not for: use as a general assistant. ## README ````markdown # Qwen3.6-35B-A3B-coding-reap50-GGUF Writes code with Qwen3.6-35B-A3B cut to half its experts and packed as GGUF files for llama.cpp. Made for developers who want a coding model that fits in less memory than the full model. Made by anik-jha on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: This model takes Qwen3.6-35B-A3B and drops half the experts in every layer, keeping 128 of the original 256. REAP scoring on code-focused data decided which ones stay. The pruned model was then quantized with an importance matrix into GGUF files for llama.cpp. The result has about 19B parameters, and a paper titled Half the Experts, All the Code goes with it. Who it suits: It suits developers who want a local coding model that fits where the full Qwen3.6-35B-A3B does not. ```table Industry | Who uses it | How they use it | Example Software | Developers | Run a local code assistant with less memory | Ask for a function and review the code AI research | Pruning researchers | Study expert pruning for mixture-of-experts models | Compare pruned and full-model coding scores Education | Programming students | Practice with a coding model offline | Get help with a small coding exercise Tooling | Tool builders | Back a code editor with a local llama.cpp server | Complete code at the same memory budget ``` If you want a general assistant for non-coding work, you can skip it, since the card warns against that use. Where to use it: It runs anywhere llama.cpp runs, on Windows, macOS or Linux. - llama.cpp and apps built on it - Local coding workflows on machines with enough memory for the file size - Windows, macOS or Linux ```table Use case | Who | What they get back Code generation | Developers | Code written by the pruned model Benchmark comparison | Researchers | Scores to compare with the full model's low-bit versions Reproducing the pruning | Model builders | An expert selection file in the moep repository ``` How to set it up: You need Python for the download tool and a llama.cpp build. Pick one of the two GGUF files, which are 11.4 GB and 13.3 GB. 1. Install the Hugging Face hub tools. 2. Download the repository files. 3. Point llama.cpp at the GGUF file you chose. ```sh pip install -U huggingface_hub hf download anik-jha/Qwen3.6-35B-A3B-coding-reap50-GGUF ``` How to use it: Load the GGUF file in llama.cpp, or an app built on it, and give it coding tasks. The card's tests turned reasoning off. The card part shown has no llama.cpp command, so use your own llama.cpp setup for the exact call. ```table File | Size | Note Q4_K_M with importance matrix | 11.4 GB | Smaller file, slightly lower scores Q5_K_M with importance matrix | 13.3 GB | Larger file, the best scores in the card's table ``` Example: You load the Q4_K_M file in llama.cpp and ask it to write a small Python function. It returns code. The card does not show a sample reply, only benchmark scores for the file. For newcomers and experts: A mixture-of-experts model has many specialist blocks, and only a few run for each token. Pruning removes half of them. To try it, start with the smaller file and a simple coding request. The pruning used REAP scoring on code-heavy data, so general knowledge suffers while coding holds up. The card reports that general perplexity roughly doubles. Scores come from greedy pass@1 with EvalPlus against llama.cpp, with reasoning off. ```flow Start with Qwen3.6-35B-A3B Score experts on coding data with REAP Remove half of the experts Quantize with an importance matrix Run the GGUF file in llama.cpp ``` Good to know: At a similar memory budget, the card says these files beat a 2-bit version of the full model on HumanEval+. ```chart Title: HumanEval+ score, greedy pass@1 Q5_K_M pruned: 0.915 score Q4_K_M pruned: 0.902 score Full model IQ2_M: 0.896 score Full model Q8: 0.890 score ``` - Trade-off: general perplexity roughly doubles, so treat it as a coder and keep it out of general assistant roles. - The full-model rows in the card are for comparison only and are not included here. - Reproduction: the expert selection file is in the moep repository, so the pruning can be redone from the base model. - License: Apache 2.0, as a derivative of Qwen3.6-35B-A3B. - Cost to run: none named. - Data it reaches: the prompts and code you give it, handled on your own machine. - Not for: use as a general assistant. ## On Hugging Face, 13 November 2026 - Library: llama.cpp - Parameters: 18.5B - Weights: about 9.3 GB at 4-bit (estimate) - Formats: GGUF - Downloads in the last 30 days: 3,898 - Likes: 16 - License: apache-2.0 - Based on: Qwen/Qwen3.6-35B-A3B - Tags: llama.cpp, gguf, mixture-of-experts, pruning, code, imatrix, conversational ## Links - Model: https://huggingface.co/anik-jha/Qwen3.6-35B-A3B-coding-reap50-GGUF - Files: https://huggingface.co/anik-jha/Qwen3.6-35B-A3B-coding-reap50-GGUF/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download anik-jha/Qwen3.6-35B-A3B-coding-reap50-GGUF ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [anik-jha/Qwen3.6-35B-A3B-coding-reap50-GGUF on Hugging Face](https://huggingface.co/anik-jha/Qwen3.6-35B-A3B-coding-reap50-GGUF) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | Qwen3.6-35B-A3B-coding-reap50-GGUF (this page) | 3,898 | 16 | 18.5B | apache-2.0 | 2026-10-18 | | [Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF](https://mindket.com/p/06acb609-98ee-4422-8521-7943aeb0bcaa) | 781,625 | 610 | 117B | apache-2.0 | 2026-10-19 | | [Qwen 3.6 35B-A3B REAP-48 v2 GGUF](https://mindket.com/p/303f4298-cc6d-452d-a68a-d4be1ae2a110) | 2,427 | 34 | 19.2B | apache-2.0 | 2026-08-25 | | [DeepSeek-V4.1-Flash-1017-GSQ-RCO-Coder-GGUF](https://mindket.com/p/1350113a-de6f-4d62-96d6-599c30da33a2) | 342,280 | 225 | 197B | mit | 2026-11-02 | | [POCKET-35B-GGUF](https://mindket.com/p/ac8c34ef-3e4c-4644-9827-a45715da0786) | 452,730 | 91 | 34.7B | apache-2.0 | 2026-11-09 | | [GLM-5.3-Flash Maya GGUF](https://mindket.com/p/af050023-ccbe-464c-bec4-5b26b64ca503) | 1,276,300 | 109 | 4.1K | mit | 2026-11-11 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-10-18 - First published: 2026-07-18 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open anik-jha/Qwen3.6-35B-A3B-coding-reap50-GGUF on Hugging Face](https://huggingface.co/anik-jha/Qwen3.6-35B-A3B-coding-reap50-GGUF) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/621f09f3-06cf-48a3-836b-eea19489d58b) - [Its page on Mindket](https://mindket.com/p/621f09f3-06cf-48a3-836b-eea19489d58b)