Run lmstudio-community/Llama-3.2-3B-Instruct-GGUF locally
lmstudio-community/Llama-3.2-3B-Instruct-GGUF is a mid-size instruction-tuned chat model with 3.21 billion parameters, built on the llama architecture. It is released under the llama3.2 license and has been downloaded 262,983 times.
To run lmstudio-community/Llama-3.2-3B-Instruct-GGUF locally at a 4,096-token context, its quantized versions need between 2.93 GB (Q3_K_L, lowest quality) and 4.42 GB (Q8_0, highest quality) of memory, weights plus KV cache and a system margin included.
For most users the best balance is Q8_0, needing about 4.42 GB. That means lmstudio-community/Llama-3.2-3B-Instruct-GGUF fits entirely in the VRAM of a 6 GB GPU or larger, running fully on the GPU.
All quantizations
| Quant. | Bits | Quality | Weights | KV | Total | Speed~ | Verdict |
|---|---|---|---|---|---|---|---|
| Q3_K_L | 4.52 | Good | 1.69 GB | 0.44 GB | 2.93 GB | 236.6 t/s | Fits in VRAM |
| Q4_K_M | 5.03 | Very good | 1.88 GB | 0.44 GB | 3.12 GB | 212.7 t/s | Fits in VRAM |
| Q6_K | 6.58 | Excellent | 2.46 GB | 0.44 GB | 3.7 GB | 162.5 t/s | Fits in VRAM |
| Q8_0 | 8.52 | Excellent | 3.19 GB | 0.44 GB | 4.42 GB | 125.5 t/s | Fits in VRAM |
KV cache computed from the model's exact architecture. Speed is a rough estimate bounded by memory bandwidth.
Frequently asked questions
How much VRAM do you need to run lmstudio-community/Llama-3.2-3B-Instruct-GGUF?
You need about 4.42 GB of VRAM to run lmstudio-community/Llama-3.2-3B-Instruct-GGUF entirely on the GPU using the Q8_0 quantization (at a 4,096-token context). Smaller quantizations lower the requirement at the cost of quality.
Can I run lmstudio-community/Llama-3.2-3B-Instruct-GGUF on an 8 GB GPU?
Yes. With 8 GB of VRAM you can run lmstudio-community/Llama-3.2-3B-Instruct-GGUF fully on the GPU using Q8_0 (about 4.42 GB).
Can I run lmstudio-community/Llama-3.2-3B-Instruct-GGUF on a 16 GB GPU?
Yes. With 16 GB of VRAM you can run lmstudio-community/Llama-3.2-3B-Instruct-GGUF fully on the GPU using Q8_0 (about 4.42 GB).
Can I run lmstudio-community/Llama-3.2-3B-Instruct-GGUF on a 24 GB GPU?
Yes. With 24 GB of VRAM you can run lmstudio-community/Llama-3.2-3B-Instruct-GGUF fully on the GPU using Q8_0 (about 4.42 GB).
What is the best quantization for lmstudio-community/Llama-3.2-3B-Instruct-GGUF?
If memory allows, higher bits-per-weight means better quality. A common sweet spot is a Q4_K_M or Q5_K_M quantization, which keeps most of the quality while roughly halving the memory versus 8-bit. Pick the highest quantization that still fits in your VRAM.