Products · Raspberry Pi · Board
Raspberry Pi 4 Model B
- Chip
- Broadcom BCM2711
- Unified memory
- 2, 4 or 8 GB
- Launch price
- $45–$75
- Released
- 2019
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 BCM2711 | 2.0 GB | 1.2 GB | 13 GB/s | 23 of 619 | $45 |
| Broadcom BCM2711 | 4.0 GB | 2.8 GB | 13 GB/s | 30 of 619 | $55 |
| Broadcom BCM2711 | 8.0 GB | 6.4 GB | 13 GB/s | 31 of 619 | $75 |
Specifications 4.0 GB configuration
| Maker | Raspberry Pi |
|---|---|
| Type | Board |
| Chip | Raspberry Pi 4 (4 GB) |
| Unified memory | 4.0 GB |
| Usable for AI models | 2.8 GB |
| Memory bandwidth | 13 GB/s |
| FP16 compute | 0.1 TFLOPS |
| Notes | BCM2711, 4× Cortex-A72 at 1.8 GHz. Launch prices (2019, 8 GB in 2020). Raspberry Pi’s December 2025 list prices are $45 (2 GB), $60 (4 GB) and $85 (8 GB). |
| Product page | www.raspberrypi.com (opens in a new tab) |
Best LLMs for the Raspberry Pi 4 Model B 4.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | LFM3 1.7B | Q5_K_M | 2.2 GB | 3.1 tok/s | Slow |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM5 2B | Q3_K_M | 2.4 GB | 3.4 tok/s | Slowtight fit |
| 47Fair quality (C) · 47 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. | LFM3-VL 2B | Q4_K_M | 2.1 GB | 3.4 tok/s | Slow |
| 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Spark-X2.6 4B | Q2_K | 2.8 GB | 2.6 tok/s | Very slowtight fit |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Unlimited OCR 2 (3B-A0.6B) | Q2_K | 2.7 GB | 17.0 tok/s | Runs welltight fit |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-OCR 1.0 1.3B | Q4_K_M | 1.7 GB | 5.0 tok/s | Slow |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | TMax 4B | Q2_K | 2.8 GB | 2.6 tok/s | Very slowtight fit |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 1B | Q4_K_M | 1.9 GB | 4.2 tok/s | Slow |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | TMax 2B | Q4_K_M | 2.1 GB | 3.5 tok/s | Slow |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Unlimited OCR (3B-A0.6B) | Q2_K | 2.7 GB | 17.0 tok/s | Runs welltight fit |
Best Image models for the Raspberry Pi 4 Model B 4.0 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 56/100 (quality, fit, speed and memory use) sets the ranking. | SD Turbo | FP16 | 2.6 GB | 21 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 54/100 (quality, fit, speed and memory use) sets the ranking. | Realistic Vision V5.1 | FP16 | 2.5 GB | 5.2 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 53/100 (quality, fit, speed and memory use) sets the ranking. | DreamShaper 8 | FP16 | 2.5 GB | 5.2 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 52/100 (quality, fit, speed and memory use) sets the ranking. | LCM DreamShaper v7 | FP16 | 2.5 GB | 65 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 51/100 (quality, fit, speed and memory use) sets the ranking. | PixArt-Σ XL 1024 | FP16 | 2.3 GB | 8.0 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 1.5 | FP16 | 2.5 GB | 5.2 min | Very slowtight fit · encoder unloaded after use |
Best Video models for the Raspberry Pi 4 Model B 4.0 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) | FP16 | 2.6 GB | 1.8 h | Very slowtight fit · CPU offload |
Best Decision models for the Raspberry Pi 4 Model B 4.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 86Excellent quality (A+) · 86 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 v3.5 | Q8_0 | 1.7 GB | 10.4 s | Very slow |
| 84Great quality (A) · 84 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. | Jina Reranker v3 | Q8_0 | 1.7 GB | 10.4 s | Very slow |
| 78Great quality (A) · 78 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. | OpenAI Privacy Filter | Q8_0 | 2.4 GB | 468 ms | Slowtight fit |
| 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. | GLiNER2.5 Decide | Q8_0 | 1.2 GB | 4.5 s | Very slow |
| 80Great quality (A) · 80 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. | FRIDA-Decisions | Q8_0 | 1.7 GB | 7.6 s | Very slow |
| 80Great quality (A) · 80 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. | Qwen3 Reranker 0.6B | Q8_0 | 1.7 GB | 10.4 s | Very slow |
| 81Great quality (A) · 81 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-large v2 | Q6_K | 2.1 GB | 26.6 s | Very slow |
| 76Great quality (A) · 76 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. | Llama Prompt Guard 2 86M | Q8_0 | 1.0 GB | 5.2 s | Very 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.