Products · Raspberry Pi · Board
Raspberry Pi 5
- Chip
- Broadcom BCM2712
- Unified memory
- 2, 4, 8 or 16 GB
- Launch price
- $50–$120
- Released
- 2023
Configurations
Pick one to see which models it runs. More memory lets larger models fit; bandwidth sets how fast they answer.
| Configuration | Memory | Usable for AI | Bandwidth | LLMs that run well | Launch price |
|---|---|---|---|---|---|
| Broadcom BCM2712 | 2.0 GB | 1.2 GB | 17 GB/s | 28 of 619 | $50 |
| Broadcom BCM2712 | 4.0 GB | 2.8 GB | 17 GB/s | 84 of 619 | $60 |
| Broadcom BCM2712 | 8.0 GB | 6.4 GB | 17 GB/s | 96 of 619 | $80 |
| Broadcom BCM2712 | 16.0 GB | 13.6 GB | 17 GB/s | 103 of 619 | $120 |
Specifications 2.0 GB configuration
| Maker | Raspberry Pi |
|---|---|
| Type | Board |
| Chip | Raspberry Pi 5 (2 GB) |
| Unified memory | 2.0 GB |
| Usable for AI models | 1.2 GB |
| Memory bandwidth | 17 GB/s |
| FP16 compute | 0.2 TFLOPS |
| Notes | BCM2712, 4× Cortex-A76 at 2.4 GHz. Launch prices: $60 (4 GB) and $80 (8 GB) in October 2023, $50 (2 GB) in August 2024, $120 (16 GB) in January 2025. Raspberry Pi has raised prices several times since December 2025 as memory costs rose; the 16 GB board is $385 from 2 November 2026. The 1 GB version ($45) is too small for language models and isn’t listed. |
| Product page | www.raspberrypi.com (opens in a new tab) |
Best LLMs for the Raspberry Pi 5 2.0 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 350M | 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 0.8B | 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 350M | 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 350M | 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 450M | 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 230M | 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 700M | 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 Instruct | 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 2.5 | 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 Instruct | Q2_K | 1.0 GB | 58.6 tok/s | Runs great |
Best Image models for the Raspberry Pi 5 2.0 GB
None of the image models in our catalog fit in this much memory.
Best Video models for the Raspberry Pi 5 2.0 GB
None of the video models in our catalog fit in this much memory.
Best Decision models for the Raspberry Pi 5 2.0 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 86M | 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 22M | 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 v3 | 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 Base | 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 v3 | 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 v2 | 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 v2 | 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 R2 | Q8_0 | 0.8 GB | 932 ms | Slow |
Spec sources
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.