Hardware · Raspberry Pi

What AI models can the Raspberry Pi 4 (2 GB) run?

RAM: 2.0 GB
Usable for models: 1.2 GB
Memory bandwidth: 13 GB/s
Runs models on: CPU cores
Released: 2019

36 / 619 LLMs run Best: LFM2.5 230M 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. The Hailo AI HATs need the Pi 5’s PCIe connector.

More about this hardware

Maker	Raspberry Pi
Type	Single-board computer or edge AI board
Share of memory for models	60% (what Linux typically leaves free on a board this size)
Chip	Broadcom BCM2711
AI accelerator	No NPU. The Hailo AI HATs need the Pi 5’s PCIe connector.
Boards with this chip	Raspberry Pi 4 Model B · Raspberry Pi 400 · Compute Module 4
Memory type	LPDDR4-3200, 32-bit
Bandwidth figure	12.8 GB/s, the chip’s rated memory speed
Note	4× Cortex-A72 at 1.8 GHz (1.5 GHz on early boards). Its cores read memory far more slowly than a Pi 5’s, so we assume 30% of the rated speed (estimate): small models (1-3B) at a few tokens per second. Needs the 64-bit OS. The 1 GB version leaves too little memory for language models and isn’t listed.
Specifications	www.raspberrypi.com

Apps that run models well on the Raspberry Pi 4 (2 GB)

Linux on ARM boards

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 4 (2 GB)

Raspberry Pi 4 Model BRaspberry Pi · Board · 2, 4 or 8 GB · $45–$75Product page (opens in a new tab)

Best LLMs for the Raspberry Pi 4 (2 GB)

Quality	Model	Quant	Memory	Speed	Runs
8Basic quality (D) · 8 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.	LFM2.5 230MLiquid AI	`Q3_K_M`	0.9 GB	36.8 tok/s	Runs great
9Basic quality (D) · 9 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.	LFM2.5 350MLiquid AI	`Q2_K`	0.9 GB	30.7 tok/s	Runs great
8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.	Granite 4.0 H 350MIBM	`Q2_K`	0.9 GB	31.6 tok/s	Runs great
8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.	LFM2 350MLiquid AI	`Q2_K`	0.9 GB	30.7 tok/s	Runs great
4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.	SmolVLM 256M InstructHugging Face	`Q2_K`	1.0 GB	41.4 tok/s	Runs great
4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 3 270MGoogle	`Q2_K`	0.8 GB	39.8 tok/s	Runs great
3Basic quality (D) · 3 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.	SmolLM2 135M InstructHugging Face	`Q5_K_M`	1.0 GB	41.6 tok/s	Runs great
2Basic quality (D) · 2 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.	Falcon-H1 Tiny 90M InstructTII	`Q6_K`	0.9 GB	50.5 tok/s	Runs great
1Basic quality (D) · 1 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.	SmolLM 135M InstructHugging Face	`Q5_K_M`	0.8 GB	41.6 tok/s	Runs great
18Basic quality (D) · 18 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.5 0.8BAlibaba	`Q2_K`	1.1 GB	12.4 tok/s	Runs welltight fit
8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.	LFM2-VL 450MLiquid AI	`Q2_K`	1.0 GB	23.9 tok/s	Runs well
4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.	ERNIE 4.5 0.3BBaidu	`Q2_K`	1.0 GB	29.9 tok/s	Runs well

Best Image models for the Raspberry Pi 4 (2 GB)

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

Best Video models for the Raspberry Pi 4 (2 GB)

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

Best Decision models for the Raspberry Pi 4 (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 76/100 (quality, fit, speed and memory use) sets the ranking.	Llama Prompt Guard 2 86MMeta	`Q8_0`	1.0 GB	5.2 s	Very slow
74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	GLiClass ModernBERT Large v3Knowledgator	`Q8_0`	1.1 GB	3.7 s	Very slowtight fit
68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	Llama Prompt Guard 2 22MMeta	`Q8_0`	0.7 GB	1.3 s	Slow
75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	mxbai-rerank-base v2Mixedbread	`Q6_K`	1.1 GB	8.5 s	Very slowtight fit
70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	GTE Reranker ModernBERT BaseAlibaba	`Q8_0`	0.8 GB	2.8 s	Very slow
72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	DeBERTa v3 Large Zero-shot v2.0Moritz Laurer	`Q8_0`	1.2 GB	4.1 s	Very slowtight fit
70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v2 Base MultilingualJina AI	`Q8_0`	1.0 GB	5.2 s	Very slow
68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	Granite Embedding Reranker English R2IBM	`Q8_0`	0.8 GB	2.8 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.