- huggingface
- Ryzen AI Max+ 395
- Labels
- Image
- Text
- VLM
- Generation
- Build
- Embedl-optimized
- Precision
- W4A4
- Runtime
- llama.cpp with Embedl optimizations
- Context length
- 8,192 tokens
Google's largest dense Gemma 4 model, for reasoning, coding and long documents, with images.
Methodology
- Throughput: one user, real conversations from the public OpenAssistant set, 2,048 tokens in, 128 out, greedy, no prompt reuse. Average of 20 requests after 3 warm-up requests. Baseline llama.cpp runs with its default server settings. End-to-end is the whole request.
- Power and memory: sampled on the device during those runs. Idle is the device at rest before the run; energy per token is the run's energy over its generated tokens; peak memory is the model server's.
- Accuracy: full test sets, greedy, the same model files and settings as served. GSM8K 1319, IFEval 541, MMLU-Pro 1008 questions.
- Baseline llama.cpp: the published weights on upstream llama.cpp, same settings, same device.
- Reproduce:
embedl bench google/gemma-4-31B-it/ryzen-ai-max-395on your device.
Files
Variants
Every build of Gemma 4 31B on Ryzen AI Max+ 395.