Downloads · 30 days
62
35% of all-time downloads
Qwen3-8B-Power
librepowerai/Qwen3-8B-Power
Qwen3-8B-Power is a machine learning model from librepowerai. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Qwen3-8B quantized to Q4KM with a Q6K output head for fast CPU inference on IBM Power — POWER9 (VSX) and POWER10/11 (MMA-accelerated) via LibrePower. No GPU required. Size: 4.7G.
All-time downloads
178
Public
Repo size
10.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf10.1 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jun 12, 2026
- Updated
- Jun 12, 2026
- SHA
- 8b44290d
Base models
Model card
From the Hugging Face model README
Qwen3-8B — Q4_K_M for IBM Power (Linux ppc64le + AIX)
Qwen3-8B quantized to Q4_K_M with a Q6_K output head for fast CPU inference on IBM Power — POWER9 (VSX) and POWER10/11 (MMA-accelerated) via LibrePower. No GPU required. Size: 4.7G.
Run it
Ubuntu / Debian ppc64le:
curl -fsSL https://linux.librepower.org/install.sh | sudo sh
sudo apt install librepower-llama
wget https://huggingface.co/librepowerai/Qwen3-8B-Power/resolve/main/Qwen3-8B-Q4_K_M.gguf
lp-llama-completion -m Qwen3-8B-Q4_K_M.gguf -p "Hello!" -n 64 -t $(nproc)
IBM AIX 7.3 (big-endian):
dnf install llama-aix
wget https://huggingface.co/librepowerai/Qwen3-8B-Power/resolve/main/Qwen3-8B-Q4_K_M-be.gguf
lp-llama-completion -m Qwen3-8B-Q4_K_M-be.gguf -p "Hello!" -n 64 -t $(nproc)
Files
Qwen3-8B-Q4_K_M.gguf— little-endian (Ubuntu/Linux ppc64le)Qwen3-8B-Q4_K_M-be.gguf— big-endian (IBM AIX)
Good for
Top-quality 8B: complex reasoning, code, RAG, agents (hybrid thinking — use /no_think for low latency)
Credits
Base model by its original authors (Apache-2.0). Quantization & Power packaging: LibrePower.
- License
- apache-2.0
- Created
- Jun 12, 2026
- Updated
- Jun 12, 2026