Edge LLM Leaderboard: Raspberry Pi 5 — leaderboard
Edge LLM Leaderboard: Raspberry Pi 5 evaluates model capability on inference tasks from the linked upstream source with MMLU Accuracy as the primary reported metric.
Metric: MMLU Accuracy (%). Source: huggingface.co. 128 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Mistral-7B-Instruct-v0.3 (Q8_0, llama_cpp) | 43.2 |
| 2 | Mistral-7B-Instruct-v0.3 (Q4_K_M, llama_cpp) | 42.9 |
| 3 | Mistral-7B-Instruct-v0.3 (Q4_0_4_4, llama_cpp) | 42.9 |
| 4 | Phi-3-medium-128k-instruct (Q4_K_M, llama_cpp) | 42.7 |
| 5 | Qwen2.5-14B (Q4_K_M, llama_cpp) | 42.5 |
| 6 | gemma-2-9b (Q8_0, llama_cpp) | 42.4 |
| 7 | gemma-2-9b (Q4_0_4_4, llama_cpp) | 42.4 |
| 8 | Qwen2.5-14B (Q4_0_4_4, llama_cpp) | 42.1 |
| 9 | Phi-3-medium-128k-instruct (Q4_0_4_4, llama_cpp) | 42.1 |
| 10 | Mistral-Nemo-Base-2407 (Q4_0_4_4, llama_cpp) | 41.9 |
Interactive version: theaggregate.ai/benchmark?slug=edge-llm-leaderboard-raspberry-pi-5 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.