schuttdev/hipfire-qwen3-8b

Qwen3-8B for hipfire

Pre-quantized Qwen3-8B (LLaMA (standard attention)) for hipfire, a Rust-native LLM inference engine for AMD RDNA GPUs.

Quantized from Qwen/Qwen3-8B.

Files

File	Quant	Size	Min VRAM	Speed (5700 XT)
qwen3-8b.q4.hfq	HFQ4	4.1GB	6GB	59.9 tok/s
qwen3-8b-q4k-all.hfq	Q4_K	4.3GB	6GB	—

Usage

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

# Pull and run
hipfire pull qwen3:8b
hipfire run qwen3:8b "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.