Smaller alternatives
Models that need less memory than Llama 3.2 3B and score about as well or better.
No scored model is both smaller and about as intelligent as Llama 3.2 3B.
Llama 3.2 3B Instruct
Meta · 3.2B · Dense
Llama 3.2 3B Instruct is a 3.2B model from Meta with a 128K-token context. At Q4_K_M with an 8K context it needs about 3.1 GB; 5 GB leaves room for longer chats.
Quantization options
| Quant | Bits | Memory | Quality | On your hardware |
|---|---|---|---|---|
| Q2_K | 3.16 | — | Noticeably worse | … |
| Q3_K_M | 4 | — | Some loss | … |
| Q4_K_M | 4.89 | — | Good | … |
| Q5_K_M | 5.7 | — | Good | … |
| Q6_K | 6.56 | — | Near original | … |
| Q8_0 | 8.5 | — | Near original | … |
| F16 | 16 | — | Original | … |
Memory by context length
At Q4_K_M. The context cache grows with every token the model keeps in mind.
| Context | Context cache | Total |
|---|---|---|
| 4K | 0.4 GB | 2.6 GB |
| 8K | 0.9 GB | 3.1 GB |
| 32K | 3.5 GB | 5.7 GB |
| 128K | 14 GB | 16.2 GB |
Next steps
Compare it with
Scored models of a similar size, side by side on your device.
Least hardware that runs it well
Desktop devices with the least memory that give Llama 3.2 3B grade A or S at Q4_K_M.
Can I run Llama 3.2 3B Instruct locally?
Can I run Llama 3.2 3B Instruct locally?
Yes, if your GPU or Mac has about 3.1 GB free for it at Q4_K_M. Open this page on that computer to see the grade for your exact hardware, then start it with llama.cpp, Ollama or LM Studio.
How much memory does Llama 3.2 3B Instruct need?
About 3.1 GB at Q4_K_M with an 8K context and 4.4 GB at Q8_0. Lower quantizations fit smaller cards with some loss in quality; longer contexts add to the total.