schuttdev/hipfire-qwen3.5-9b

Qwen3.5-9B for hipfire

Pre-quantized Qwen3.5-9B (DeltaNet hybrid) for hipfire, a Rust-native LLM inference engine for AMD RDNA GPUs.

Quantized from Qwen/Qwen3.5-9B.

Files

File	Quant	Size	Min VRAM	Speed (5700 XT)
qwen3.5-9b.q4.hfq	HFQ4	4.5GB	6GB	45 tok/s
qwen3.5-9b.hfq6.hfq	HFQ6	6.8GB	8GB	37 tok/s

Usage

# Install hipfire
curl -L https://raw.githubusercontent.com/Kaden-Schutt/hipfire/master/scripts/install.sh | bash

# Pull and run
hipfire pull qwen3.5:9b
hipfire run qwen3.5:9b "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
• All models: docs/MODELS.md

License

Model weights subject to original Qwen license. hipfire engine: MIT.