Can it run?
Runs well
Using Q5_K_M in Ollama
Fit status
Runs well
Decode
272.8 tok/s
TTFT
710 ms
Safe context
31K
Memory
5.2 GB / 10.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 272.8 tok/s | 1032 ms | 60K |
| Chat | C | Runs well | 272.8 tok/s | 387 ms | 16K |
| Coding | C | Runs well | 272.8 tok/s | 710 ms | 31K |
| RAG | C | Runs well | 272.8 tok/s | 1291 ms | 60K |
| Reasoning | C | Runs well | 272.8 tok/s | 839 ms | 31K |
How Llama 3.2 3B Instruct (3B params) fits at each quantization level on RTX 3080 10GB (10.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 1.2 GB | Low | D32 |
Q3_K_S | 3 | 1.5 GB | Low | D33 |
NVFP4 | 4 | 1.7 GB | Medium | D33 |
Q4_K_M | 4 | 1.8 GB | Medium | D33 |
Q5_K_M | 5 | 2.2 GB | High | D34 |
Q6_K | 6 | 2.5 GB | High | D35 |
Q8_0 | 8 | 3.2 GB | Very High | D36 |
F16Best for your GPU | 16 | 6.1 GB | Maximum | C43 |
huggingface-cli download hf-bartowski--llama-3-2-3b-instruct-gguf