StableLM 2 12B Chat on Raspberry Pi 4 (4 GB)

Can the Raspberry Pi 4 (4 GB) run StableLM 2 12B Chat?

No, it doesn’t fit

No. StableLM 2 12B Chat needs about 6.5 GB even at Q2_K; the Raspberry Pi 4 (4 GB) has 2.8 GB usable.

Download StableLM 2 12B Chat

Recommended: Q2_K. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run stablelm2:12b-chat-q2_K

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q2_K file (opens in a new tab)

huggingface.co/stabilityai/stablelm-2-12b-chat-GGUF (opens in a new tab)

ollama run hf.co/stabilityai/stablelm-2-12b-chat-GGUF:Q2_K

Original weights · Hugging Face

Full-precision files from Stability AI, for fine-tuning, vLLM, Transformers.

huggingface.co/stabilityai/stablelm-2-12b-chat (opens in a new tab)

No sign-in needed.

Links checked 5 hours ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 19Basic quality (D) · 19 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 2/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q2_K, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Won't run: How well it runs on the Raspberry Pi 4 (4 GB): speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	2.6 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	0.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	0.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	0.0 / 15
Match score	2.6 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

It doesn’t fit, so only a reduced share of the quality points counts and fit, speed and memory use score zero.

Every quantization on the Raspberry Pi 4 (4 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	6.5 GB	2.8 GB	—	Won't run	19Basic quality (D) · 19 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 2/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	7.6 GB	2.8 GB	—	Won't run	23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	9.1 GB	2.8 GB	—	Won't run	26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	10.3 GB	2.8 GB	—	Won't run	27Basic quality (D) · 27 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	11.6 GB	2.8 GB	—	Won't run	27Basic quality (D) · 27 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	14.5 GB	2.8 GB	—	Won't run	28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	25.9 GB	2.8 GB	—	Won't run	28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 4K of context. Longer conversations or documents grow the KV cache.

Hardware that can run it

28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q8_0 · 42.6 tok/s · Runs great
28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q8_0 · 48.2 tok/s · Runs great
28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q8_0 · 51.9 tok/s · Runs great
27Basic quality (D) · 27 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q6_K · 47.1 tok/s · Runs great
27Basic quality (D) · 27 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q6_K · 51.6 tok/s · Runs great
27Basic quality (D) · 27 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti Q6_K · 62.9 tok/s · Runs great

Models that do run on the Raspberry Pi 4 (4 GB)

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 · 3.1 tok/s
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 · 3.4 tok/s
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 · 3.4 tok/s
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 · 2.6 tok/s
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 · 17.0 tok/s

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.