Raspberry Pi 5

Hardware · Raspberry Pi

What AI models can the Raspberry Pi 5 (2 GB) run?

RAM
2.0 GB
Usable for models
1.2 GB
Memory bandwidth
17 GB/s
Runs models on
CPU cores
Released
2023
36 / 619 LLMs run Best: LFM2.5 350M 0 / 60 Image models run None fit 0 / 43 Video models run None fit 25 / 70 Decision models run Best: Llama Prompt Guard 2 86M

Models run on the CPU cores here, so the memory’s speed and how fast those cores can read it set the pace: small models (about 1-4B) are usable, bigger ones are slow. We plan around 1.2 GB of the 2.0 GB (what Linux leaves free for a model). No NPU. Raspberry Pi’s AI Kit and AI HAT+ (Hailo-8L, 13 TOPS; Hailo-8, 26 TOPS) run vision models only. The AI HAT+ 2 (Hailo-10H, 40 TOPS, with its own 8 GB) also runs a few 1.5B LLMs, but in CNX Software’s test it was slower than the Pi’s own CPU.

More about this hardware

MakerRaspberry Pi
TypeSingle-board computer or edge AI board
Share of memory for models60% (what Linux typically leaves free on a board this size)
ChipBroadcom BCM2712
AI acceleratorNo NPU. Raspberry Pi’s AI Kit and AI HAT+ (Hailo-8L, 13 TOPS; Hailo-8, 26 TOPS) run vision models only. The AI HAT+ 2 (Hailo-10H, 40 TOPS, with its own 8 GB) also runs a few 1.5B LLMs, but in CNX Software’s test it was slower than the Pi’s own CPU.
Boards with this chipRaspberry Pi 5 · Raspberry Pi 500 / 500+ · Compute Module 5
Memory typeLPDDR4X-4267, 32-bit
Bandwidth figure17.1 GB/s, the chip’s rated memory speed
Note4× Cortex-A76 at 2.4 GHz. llama.cpp and Ollama run on the CPU; the VideoCore VII GPU isn’t used for LLMs. Speeds assume the CPU reads about 60% of the memory’s rated 17 GB/s, in line with published llama.cpp results (roughly 11-21 tokens/s for Llama 3.2 1B and about 5 for 3B at Q4_K_M). Use the Active Cooler. The 1 GB version leaves too little memory for language models and isn’t listed.
Specificationswww.raspberrypi.com

Apps that run models well on the Raspberry Pi 5 (2 GB)

Linux on ARM boards

  1. OllamaOne command with Ollama’s own build of this model.
  2. LM StudioPoint-and-click: search, download and chat in one window.
  3. llama.cppUsually the first to support new model architectures.
  4. Docker Model RunnerHandy if you already work in Docker.

For a typical model that fits in memory. Each model page picks the best app for that model on this hardware. All apps

1 product with the Raspberry Pi 5 (2 GB)

Best LLMs for the Raspberry Pi 5 (2 GB)

Quality Model Quant Memory Speed Runs
13Basic quality (D) · 13 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 350MLiquid AI Q4_K_M 1.0 GB 50.0 tok/s Runs great
18Basic quality (D) · 18 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 0.8BAlibaba Q2_K 1.1 GB 33.0 tok/s Runs welltight fit
11Basic quality (D) · 11 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. Granite 4.0 H 350MIBM Q5_K_M 1.0 GB 42.5 tok/s Runs great
11Basic quality (D) · 11 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. LFM2 350MLiquid AI Q4_K_M 1.0 GB 50.0 tok/s Runs great
10Basic quality (D) · 10 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. LFM2-VL 450MLiquid AI Q3_K_M 1.0 GB 50.3 tok/s Runs great
9Basic quality (D) · 9 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. LFM2.5 230MLiquid AI Q6_K 1.0 GB 52.8 tok/s Runs great
12Basic quality (D) · 12 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. LFM2 700MLiquid AI Q2_K 1.1 GB 38.8 tok/s Runs welltight fit
11Basic quality (D) · 11 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. Falcon-H1 0.5B InstructTII Q3_K_M 1.1 GB 43.5 tok/s Runs welltight fit
10Basic quality (D) · 10 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. surya ocr 2.5Datalab Q2_K 1.1 GB 41.6 tok/s Runs welltight fit
7Basic quality (D) · 7 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. Qwen2.5 0.5B InstructAlibaba Q2_K 1.0 GB 58.6 tok/s Runs great
14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. Gemma 3 1BGoogle Q2_K 1.1 GB 28.7 tok/s Runs welltight fit
5Basic quality (D) · 5 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. Gemma 3 270MGoogle Q6_K 1.0 GB 45.0 tok/s Runs great

Best Image models for the Raspberry Pi 5 (2 GB)

None of the image models in our catalog fit in this much memory.

Best Video models for the Raspberry Pi 5 (2 GB)

None of the video models in our catalog fit in this much memory.

Best Decision models for the Raspberry Pi 5 (2 GB)

Quality Model Quant Memory Speed Runs
76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Llama Prompt Guard 2 86MMeta Q8_0 1.0 GB 1.7 s Very slow
68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. Llama Prompt Guard 2 22MMeta Q8_0 0.7 GB 443 ms Slow
74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. GLiClass ModernBERT Large v3Knowledgator Q8_0 1.1 GB 1.2 s Slowtight fit
70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. GTE Reranker ModernBERT BaseAlibaba Q8_0 0.8 GB 932 ms Slow
66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. GLiClass Base v3Knowledgator Q8_0 0.8 GB 591 ms Slow
52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. ms-marco MiniLM L6 v2Sentence Transformers Q8_0 0.6 GB 146 ms Runs well
75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. mxbai-rerank-base v2Mixedbread Q6_K 1.1 GB 2.8 s Very slowtight fit
68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. Granite Embedding Reranker English R2IBM Q8_0 0.8 GB 932 ms Slow

Best LLMs by task on this hardware Open in Model Finder

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

Was this page helpful?