Phones, tablets, old laptops, and the fastest local proof.
SBC / Embedded
Can Raspberry Pi 5 (8 GB) run Gemma 4?
8 GB memory profile for local Gemma 4 testing. The checker below ranks Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B specifically for Raspberry Pi 5 (8 GB).
Better phones, Apple silicon laptops, and mainstream desktops.
16GB+ unified-memory Macs and desktops with room for context.
The instruct 12B when you want chat, vision, and a 256K window on 16GB+ machines.
Strong desktop GPUs and disciplined 24GB+ Apple silicon setups.
Gemma-family MoE when you want the newer diffusion decode path and multimodal prompts.
High-end workstations where local quality matters more than convenience.
Full Model Directory
Explore 130+ Other Open-Weight Models on This Hardware
Compare Llama 3.3, Qwen 3, DeepSeek-R1, Mistral, and Phi on Raspberry Pi 5 (8 GB), or run a side-by-side GPU and Apple Silicon benchmark comparison.
Hardware Memory Analysis
Usable Memory Pool & Bandwidth Profile for Raspberry Pi 5 (8 GB)
Raspberry Pi 5 (8 GB) runs inference directly on ARM CPU cores backed by shared LPDDR system memory (8 GB profile, ~32 GB/s bandwidth). Without a high-bandwidth discrete GPU, token speed scales closely with raw LPDDR bandwidth and keeping total memory below ~70% (5.6 GB) prevents Linux swap thrashing.
Practical Model Budget
5.6 GB
Memory Bandwidth
~32 GB/s
Recommended Checkpoint
Gemma 4 E2B (Q4_K_M)
Gemma 4 Checkpoint Compatibility Matrix on Raspberry Pi 5 (8 GB)
Evaluated at Q4_K_M baseline weights plus 0.5 GB baseline runtime overhead against Raspberry Pi 5 (8 GB)'s 5.6 GB usable budget. Leave at least 1.5–4 GB spare headroom for multi-turn KV cache expansion.
| Model | Q4_K_M Memory | Est. Speed | Grade | Practical Headroom Verdict |
|---|---|---|---|---|
| Gemma 4 E2B | 3.1 GB | ~7 tok/s | Tight fit | Clean fit (+2.5 GB spare for 4K–8K context) |
| Gemma 4 E4B | 4.6 GB | ~5 tok/s | Barely runs | Tight fit — use Q8_0 KV cache and short context |
| Gemma 4 12B | 7.1 GB | -- | Too heavy | Exceeds on-device memory budget |
| Gemma 4 12B IT | 7.1 GB | -- | Too heavy | Exceeds on-device memory budget |
| Gemma 4 26B-A4B IT | 15.8 GB | -- | Too heavy | Exceeds on-device memory budget |
| DiffusionGemma 26B-A4B IT | 13.8 GB | -- | Too heavy | Exceeds on-device memory budget |
| Gemma 4 31B | 19 GB | -- | Too heavy | Exceeds on-device memory budget |
Single-Board Computer CPU Threading Guide for Raspberry Pi 5 (8 GB)
- Run headless `llama-cli` or `llama-server` compiled natively for ARM64 (`-mcpu=native`) with fast UHS-I/NVMe storage instead of slow microSD cards.
- Pin `-t` strictly to physical performance CPU cores and use Q4_K_M or IQ4_XS builds of E2B / small 1B–3B models.
- Use active heatsink/fan cooling so prolonged token generation does not throttle CPU frequencies.
Frequently Asked Questions for Raspberry Pi 5 (8 GB)
- What is the best Gemma 4 model to run on Raspberry Pi 5 (8 GB)?
- Based on Raspberry Pi 5 (8 GB)'s 5.6 GB practical memory budget and ~32 GB/s bandwidth, Gemma 4 E2B (Q4_K_M, 3.1 GB) is the strongest comfortable fit (~7 tok/s).
- Can Raspberry Pi 5 (8 GB) run Gemma 4 26B-A4B MoE locally?
- No. Gemma 4 26B-A4B requires ~15.8 GB at Q4_K_M, exceeding Raspberry Pi 5 (8 GB)'s 5.6 GB on-device memory budget. Use Gemma 4 E2B instead.
- How fast does Raspberry Pi 5 (8 GB) generate tokens with Gemma 4?
- With ~32 GB/s memory bandwidth, Gemma 4 E2B at Q4_K_M averages roughly 7 tokens per second when fully resident without swap or PCIe spillover.
- Which quantization format works best on Raspberry Pi 5 (8 GB)?
- Start with Q4_K_M (~4.5 bits/weight) to keep memory headroom free for 8K+ context windows. Step up to Q6_K or Q8_0 only if Q4_K_M consumes well under 60% of available VRAM or unified memory.