---
title: Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B
url: https://recentmodel.com/models/Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B/
status: just landed · new, unvetted
published: 2026-10-30T03:25:51Z
updated: 2026-10-30T11:19:53Z
source: https://huggingface.co/Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B
---

# Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B

Logics-SWE-Qwen3.6-35B-A3B is a software engineering model developed from Qwen3.6-35B-A3B using category-aware multi-teacher on-policy distillation (MOPD). Mixture-of-experts, 35B total, 3B active (256 experts, 8 per token). Context: 256K tokens (config). License: apache-2.0.


- **Org:** Logics-MLLM
- **Released:** 2026-10-30
- **Status:** just landed · new, unvetted
- **License:** apache-2.0 (permissive)
- **Parameters:** 35.1B total, 3.0B active
- **Architecture:** MoE · 256 experts, 8/token · Qwen3_5MoeForConditionalGeneration
- **Context:** 262,144 tokens
- **Task:** text-generation · text
- **Signal:** 2 HF likes · 14 downloads

## Runs on

mixed: real files + estimate; sizing calculation, not tested.

- Q4 ~22.8 GB (estimated): 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Mac 36GB, Mac 48GB, CPU only, 32GB RAM (slow)
- Q8 ~39.2 GB: 48GB GPU (RTX 6000 Ada / A6000), Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~72.0 GB: 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B)
- [Ollama](https://ollama.com/library/qwen3.6)