Hipfire Qwen3.5 2b

--- license: mit base_model: Qwen/Qwen3.5-2B tags: - hipfire - amd - rdna - quantized - qwen3.5 library_name: hipfire --- # Qwen3.5-2B for hipfire Pre-quantized **Qwen3.5-2B** (DeltaNet hybrid) for [hipfire](https://github.com/Kaden-Schutt/hipfire), a Rust-native LLM inference engine for AMD RDNA GPUs. Quantized from [Qwen/Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B). ## Files | File | Quant | Size | Min VRAM | Speed (5700 XT) | |------|-------|------|----------|-----------------| | qwen3.5-2b.q4.hfq | HFQ4 | 1.2GB | 2GB | 141 tok/s | | qwen3.5-2b.hfq6.hfq | HFQ6 | 1.6GB | 3GB | 127 tok/s | ## Usage ```bash # Install hipfire curl -L https://raw.githubusercontent.com/Kaden-Schutt/hipfire/master/scripts/install.sh | bash # Pull and run hipfire pull qwen3.5:2b hipfire run qwen3.5:2b "Hello" ``` ## Quantization Formats - **HFQ4**: 4-bit, 256-weight groups (0.53 B/w). Best speed. - **HFQ6**: 6-bit, 256-weight groups (0.78 B/w). Best quality. ~15% slower. Both include embedded tokenizer and model config. ## About hipfire Rust + HIP inference engine for AMD consumer GPUs (RDNA1–RDNA4). No Python in the hot path. 9x faster than llama.cpp+ROCm on the same hardware. - GitHub: [Kaden-Schutt/hipfire](https://github.com/Kaden-Schutt/hipfire) - All models: [docs/MODELS.md](https://github.com/Kaden-Schutt/hipfire/blob/master/docs/MODELS.md) ## License Model weights subject to original [Qwen license](https://huggingface.co/Qwen/Qwen3.5-2B). hipfire engine: MIT.