Raspberry Pi 5

Hardware · Raspberry Pi

What AI models can the Raspberry Pi 5 (4 GB) run?

RAM
4.0 GB
Usable for models
2.8 GB
Memory bandwidth
17 GB/s
Runs models on
CPU cores
Released
2023
125 / 619 LLMs run Best: LFM3 1.7B 7 / 60 Image models run Best: SD Turbo 1 / 43 Video models run Best: AnimateDiff v3 (SD 1.5) 41 / 70 Decision models run Best: OpenAI Privacy Filter

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 2.8 GB of the 4.0 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 models70% (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 (4 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 (4 GB)

Best LLMs for the Raspberry Pi 5 (4 GB)

Quality Model Quant Memory Speed Runs
53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7BLiquid AI Q4_K_M 2.0 GB 10.1 tok/s Runs well
30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. Unlimited OCR 2 (3B-A0.6B)Baidu Q2_K 2.7 GB 41.6 tok/s Runs welltight fit
42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2BLiquid AI Q3_K_M 1.9 GB 11.8 tok/s Runs well
42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 2BOpenBMB Q2_K 2.2 GB 11.4 tok/s Runs well
28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. Unlimited OCR (3B-A0.6B)Baidu Q2_K 2.7 GB 41.6 tok/s Runs welltight fit
46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. Spark-X2.6 4BSparkLLM Q2_K 2.8 GB 7.0 tok/s Slowtight fit
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. PaddleOCR-VL 1.6 0.9BBaidu Q4_K_M 1.6 GB 18.2 tok/s Runs well
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-OCR 1.0 1.3BOpenBMB Q4_K_M 1.7 GB 13.5 tok/s Runs well
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 1BOpenBMB Q4_K_M 1.9 GB 11.3 tok/s Runs well
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. TeleOCRXingChen-AGI Q4_K_M 2.6 GB 12.3 tok/s Runs welltight fit
42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. TMax 4BAi2 Q2_K 2.8 GB 6.8 tok/s Slowtight fit
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 1BOpenBMB Q4_K_M 1.7 GB 16.2 tok/s Runs well

Best Image models for the Raspberry Pi 5 (4 GB)

Quality Model Quant Memory Speed Runs
28Basic quality (D) · 28 of 100: how capable the model is at FP16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. SD TurboStability AI FP16 2.6 GB 15 s Runs welltight fit · encoder unloaded after use
42Fair quality (C) · 42 of 100: how capable the model is at FP16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. Realistic Vision V5.1SG161222 FP16 2.5 GB 3.8 min Very slowtight fit · encoder unloaded after use
40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. DreamShaper 8Lykon FP16 2.5 GB 3.8 min Very slowtight fit · encoder unloaded after use
30Basic quality (D) · 30 of 100: how capable the model is at FP16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. LCM DreamShaper v7Tsinghua (LCM) FP16 2.5 GB 48 s Slowtight fit · encoder unloaded after use
50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. PixArt-Σ XL 1024PixArt FP16 2.3 GB 5.9 min Very slowCPU offload
35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. Stable Diffusion 1.5Stability AI / Runway FP16 2.5 GB 3.8 min Very slowtight fit · encoder unloaded after use

Best Video models for the Raspberry Pi 5 (4 GB)

Quality Model Quant Memory Speed Runs
35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking. AnimateDiff v3 (SD 1.5)Shanghai AI Lab FP16 2.6 GB 78.8 min Very slowtight fit · CPU offload

Best Decision models for the Raspberry Pi 5 (4 GB)

Quality Model Quant Memory Speed Runs
78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. OpenAI Privacy FilterOpenAI Q8_0 2.4 GB 159 ms Runs welltight fit
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Jina Reranker v3.5Jina AI Q8_0 1.7 GB 3.5 s Very slow
84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Jina Reranker v3Jina AI Q8_0 1.7 GB 3.5 s Very slow
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. GLiNER2.5 DecideFastino Q8_0 1.2 GB 1.5 s Very slow
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. FRIDA-DecisionsSber AI Q8_0 1.7 GB 2.5 s Very slow
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Qwen3 Reranker 0.6BAlibaba Q8_0 1.7 GB 3.5 s Very slow
81Great quality (A) · 81 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. mxbai-rerank-large v2Mixedbread Q6_K 2.1 GB 8.9 s Very slow
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

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?