Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,146 @@
+---
+language:
+  - en
+  - ko
+  - ja
+  - zh
+license: apache-2.0
+tags:
+  - gguf
+  - qwen
+  - qwen3.6
+  - moe
+  - quantized
+  - imatrix
+  - apple-silicon
+  - ollama
+  - batiai
+  - on-device
+base_model: Qwen/Qwen3.6-35B-A3B
+pipeline_tag: text-generation
+library_name: llama.cpp
+---
+
+# Qwen 3.6 35B-A3B GGUF — Quantized by BatiAI
+
+<p align="center">
+  <a href="https://flow.bati.ai"><img src="https://img.shields.io/badge/BatiFlow-macOS%20AI%20Automation-blue?style=for-the-badge&logo=apple" alt="BatiFlow"></a>
+  <a href="https://ollama.com/batiai/qwen3.6-35b"><img src="https://img.shields.io/badge/Ollama-batiai%2Fqwen3.6--35b-green?style=for-the-badge" alt="Ollama"></a>
+</p>
+
+> imatrix-calibrated GGUF quantizations of **Qwen/Qwen3.6-35B-A3B** (text-only) for on-device AI on Mac.
+> Built and verified by [BatiAI](https://bati.ai) for [BatiFlow](https://flow.bati.ai) — free, unlimited, on-device AI automation.
+
+## Quick Start
+
+```bash
+# 16–24GB Mac
+ollama pull batiai/qwen3.6-35b:iq3
+
+# 24GB+ Mac (recommended)
+ollama pull batiai/qwen3.6-35b:iq4
+
+ollama run batiai/qwen3.6-35b:iq4
+```
+
+Aliases `:q3` and `:q4` point to the same blobs.
+
+## Available Quantizations
+
+| Tag | Quant | File Size | Min RAM | Recommended For |
+|-----|-------|-----------|---------|-----------------|
+| `:iq3` / `:q3` | **IQ3_XXS** (imatrix) | **13 GB** | 16 GB | Mac mini / MacBook Air 16GB |
+| `:iq4` / `:q4` | **IQ4_XS** (imatrix) | **18 GB** | 24 GB | MacBook Pro / Mac Studio 24GB+ |
+
+Both quants use an **importance matrix** computed from wikitext-2-raw to preserve quality at low bit-widths. IQ quants generally outperform K-quants of similar size.
+
+## Why Qwen 3.6 35B-A3B?
+
+- **MoE — 35B total, only ~3B active per token** → 9× less compute than a 27B Dense model
+- **262K native context** (1M with YaRN scaling)
+- **Gated DeltaNet hybrid attention** — long-context efficiency
+- **Function calling** — `qwen3_coder` parser (vLLM/SGLang)
+- **Agentic workflows** — tuned for repository-level coding, multi-tool reasoning
+- **Multilingual** — Korean / Japanese / Chinese / English
+- **Apache 2.0** — commercial-friendly
+
+## MoE Advantage
+
+| | 35B-A3B (MoE) | 27B (Dense) |
+|---|---|---|
+| Total params | 35B | 27B |
+| **Active params / token** | **3B** | **27B** |
+| Experts | 256 (8 routed + 1 shared) | — |
+| Typical VRAM | ~23 GB (IQ4) | ~28 GB |
+| Relative speed | **Faster** | Baseline |
+
+Only 9 of 256 experts fire per token — same reasoning, far less compute.
+
+## RAM Requirements (on-device)
+
+| Your Mac RAM | IQ3 (13 GB) | IQ4 (18 GB) |
+|--------------|-------------|-------------|
+| 16 GB        | ✅ fits (tight) | ❌ |
+| 24 GB        | ✅ comfortable  | ✅ fits (tight) |
+| 32 GB        | ✅              | ✅ comfortable  |
+| 48 GB+       | ✅              | ✅ ideal        |
+
+## Benchmarks
+
+Benchmarks on Apple Silicon will be updated as measurements come in. To reproduce on your Mac:
+
+```bash
+ollama run batiai/qwen3.6-35b:iq4 --verbose "Write a haiku about Seoul in autumn."
+```
+
+The `--verbose` flag prints prompt-eval rate, token-generation rate, and memory usage.
+
+## Note on the "3.6" Naming
+
+Upstream Qwen released this model as **Qwen 3.6** publicly. Internally the Hugging Face config still registers the architecture as `Qwen3_5MoeForConditionalGeneration` (a transitional class name carried over from the 3.5 line). llama.cpp handles this class via its `Qwen3_5MoeTextModel` converter, which is what these GGUFs were built from — text-only, vision tower excluded.
+
+## Technical Details
+
+- **Original Model**: [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B)
+- **Architecture**: MoE + Gated DeltaNet hybrid (35B total, ~3B active, 40 layers, hidden 2048)
+- **Experts**: 256 total, 8 routed + 1 shared per token
+- **Context Window**: 262,144 tokens native (extensible to ~1M via YaRN)
+- **License**: Apache 2.0
+- **Quantized with**: [llama.cpp](https://github.com/ggml-org/llama.cpp) build `bafae2765`
+- **Quantized by**: [BatiAI](https://bati.ai)
+- **Calibration data**: wikitext-2-raw
+
+## How We Quantize
+
+```
+Qwen/Qwen3.6-35B-A3B (BF16 safetensors, ~70 GB)
+  ↓ llama.cpp convert_hf_to_gguf.py  (text-only, vision excluded)
+BF16 GGUF (65 GB)
+  ↓ llama-imatrix  (wikitext-2-raw calibration, GPU-accelerated)
+imatrix.dat
+  ↓ llama-quantize --imatrix  (IQ3_XXS, IQ4_XS)
+Quantized GGUF
+  ↓ ollama push  +  hf upload
+Published to batiai/ on Ollama & Hugging Face
+```
+
+No third-party intermediaries. Direct from official Qwen weights.
+
+## About BatiFlow
+
+[**BatiFlow**](https://flow.bati.ai) is a macOS-native AI automation app — just 5 MB, Swift-native. Free on-device AI via Ollama — no API costs, no usage limits, 100% private.
+
+- **AI Command Bar** — natural-language action execution
+- **KakaoTalk / iMessage / Slack** automation
+- **Chrome** navigation, filling, screenshots via CDP
+- **57 built-in tools** — calendar, mail, reminders, files, shell, etc.
+- **Skill builder** — reusable YAML automations
+- **Multilingual** — Korean / English
+
+[Download BatiFlow](https://github.com/batiai/batiflow-releases/releases/latest)
+
+## License
+
+This repo mirrors the upstream license. `Qwen/Qwen3.6-35B-A3B` is released under **Apache 2.0** — commercial use permitted.
+
+BatiAI's quantization pipeline is MIT.