- Context
- 128Ktokens
- Released
- 2y ago
- Size
- 11Bparameters
Open-weight builds
Ollama variants
Every published Ollama tag matched to this model, including parameter editions, instruction/base variants, and quantized builds.
| Variant | Parameters | Type | Quantization | Size | Context | Input |
|---|---|---|---|---|---|---|
| llama3.2:1b-instruct-fp16 | 1B | instruct | FP16 | 2.5 GB | 128K | text |
| llama3.2:1b-instruct-q2_K | 1B | instruct | Q2_K | 581 MB | 128K | text |
| llama3.2:1b-instruct-q3_K_L | 1B | instruct | Q3_K_L | 733 MB | 128K | text |
| llama3.2:1b-instruct-q3_K_M | 1B | instruct | Q3_K_M | 691 MB | 128K | text |
| llama3.2:1b-instruct-q3_K_S | 1B | instruct | Q3_K_S | 642 MB | 128K | text |
| llama3.2:1b-instruct-q4_0 | 1B | instruct | Q4_0 | 771 MB | 128K | text |
| llama3.2:1b-instruct-q4_1 | 1B | instruct | Q4_1 | 832 MB | 128K | text |
| llama3.2:1b-instruct-q4_K_M | 1B | instruct | Q4_K_M | 808 MB | 128K | text |
| llama3.2:1b-instruct-q4_K_S | 1B | instruct | Q4_K_S | 776 MB | 128K | text |
| llama3.2:1b-instruct-q5_0 | 1B | instruct | Q5_0 | 893 MB | 128K | text |
| llama3.2:1b-instruct-q5_1 | 1B | instruct | Q5_1 | 953 MB | 128K | text |
| llama3.2:1b-instruct-q5_K_M | 1B | instruct | Q5_K_M | 912 MB | 128K | text |
| llama3.2:1b-instruct-q5_K_S | 1B | instruct | Q5_K_S | 893 MB | 128K | text |
| llama3.2:1b-instruct-q6_K | 1B | instruct | Q6_K | 1 GB | 128K | text |
| llama3.2:1b | 1B | instruct | Q8_0 | 1.3 GB | 128K | text |
| llama3.2:1b-text-fp16 | 1B | text | FP16 | 2.5 GB | 128K | text |
| llama3.2:1b-text-q2_K | 1B | text | Q2_K | 581 MB | 128K | text |
| llama3.2:1b-text-q3_K_L | 1B | text | Q3_K_L | 733 MB | 128K | text |
| llama3.2:1b-text-q3_K_M | 1B | text | Q3_K_M | 691 MB | 128K | text |
| llama3.2:1b-text-q3_K_S | 1B | text | Q3_K_S | 642 MB | 128K | text |
| llama3.2:1b-text-q4_0 | 1B | text | Q4_0 | 771 MB | 128K | text |
| llama3.2:1b-text-q4_1 | 1B | text | Q4_1 | 832 MB | 128K | text |
| llama3.2:1b-text-q4_K_M | 1B | text | Q4_K_M | 808 MB | 128K | text |
| llama3.2:1b-text-q4_K_S | 1B | text | Q4_K_S | 776 MB | 128K | text |
| llama3.2:1b-text-q5_0 | 1B | text | Q5_0 | 893 MB | 128K | text |
| llama3.2:1b-text-q5_1 | 1B | text | Q5_1 | 953 MB | 128K | text |
| llama3.2:1b-text-q5_K_M | 1B | text | Q5_K_M | 912 MB | 128K | text |
| llama3.2:1b-text-q5_K_S | 1B | text | Q5_K_S | 893 MB | 128K | text |
| llama3.2:1b-text-q6_K | 1B | text | Q6_K | 1 GB | 128K | text |
| llama3.2:1b-text-q8_0 | 1B | text | Q8_0 | 1.3 GB | 128K | text |
| llama3.2:3b-instruct-fp16 | 3B | instruct | FP16 | 6.4 GB | 128K | text |
| llama3.2:3b-instruct-q2_K | 3B | instruct | Q2_K | 1.4 GB | 128K | text |
| llama3.2:3b-instruct-q3_K_L | 3B | instruct | Q3_K_L | 1.8 GB | 128K | text |
| llama3.2:3b-instruct-q3_K_M | 3B | instruct | Q3_K_M | 1.7 GB | 128K | text |
| llama3.2:3b-instruct-q3_K_S | 3B | instruct | Q3_K_S | 1.5 GB | 128K | text |
| llama3.2:3b-instruct-q4_0 | 3B | instruct | Q4_0 | 1.9 GB | 128K | text |
| llama3.2:3b-instruct-q4_1 | 3B | instruct | Q4_1 | 2.1 GB | 128K | text |
| llama3.2:latest | 3B | instruct | Q4_K_M | 2 GB | 128K | text |
| llama3.2:3b-instruct-q4_K_S | 3B | instruct | Q4_K_S | 1.9 GB | 128K | text |
| llama3.2:3b-instruct-q5_0 | 3B | instruct | Q5_0 | 2.3 GB | 128K | text |
| llama3.2:3b-instruct-q5_1 | 3B | instruct | Q5_1 | 2.4 GB | 128K | text |
| llama3.2:3b-instruct-q5_K_M | 3B | instruct | Q5_K_M | 2.3 GB | 128K | text |
| llama3.2:3b-instruct-q5_K_S | 3B | instruct | Q5_K_S | 2.3 GB | 128K | text |
| llama3.2:3b-instruct-q6_K | 3B | instruct | Q6_K | 2.6 GB | 128K | text |
| llama3.2:3b-instruct-q8_0 | 3B | instruct | Q8_0 | 3.4 GB | 128K | text |
| llama3.2:3b-text-fp16 | 3B | text | FP16 | 6.4 GB | 128K | text |
| llama3.2:3b-text-q2_K | 3B | text | Q2_K | 1.4 GB | 128K | text |
| llama3.2:3b-text-q3_K_L | 3B | text | Q3_K_L | 1.8 GB | 128K | text |
| llama3.2:3b-text-q3_K_M | 3B | text | Q3_K_M | 1.7 GB | 128K | text |
| llama3.2:3b-text-q3_K_S | 3B | text | Q3_K_S | 1.5 GB | 128K | text |
| llama3.2:3b-text-q4_0 | 3B | text | Q4_0 | 1.9 GB | 128K | text |
| llama3.2:3b-text-q4_1 | 3B | text | Q4_1 | 2.1 GB | 128K | text |
| llama3.2:3b-text-q4_K_M | 3B | text | Q4_K_M | 2 GB | 128K | text |
| llama3.2:3b-text-q4_K_S | 3B | text | Q4_K_S | 1.9 GB | 128K | text |
| llama3.2:3b-text-q5_0 | 3B | text | Q5_0 | 2.3 GB | 128K | text |
| llama3.2:3b-text-q5_1 | 3B | text | Q5_1 | 2.4 GB | 128K | text |
| llama3.2:3b-text-q5_K_M | 3B | text | Q5_K_M | 2.3 GB | 128K | text |
| llama3.2:3b-text-q5_K_S | 3B | text | Q5_K_S | 2.3 GB | 128K | text |
| llama3.2:3b-text-q6_K | 3B | text | Q6_K | 2.6 GB | 128K | text |
| llama3.2:3b-text-q8_0 | 3B | text | Q8_0 | 3.4 GB | 128K | text |
Deployment graph
Can I run this?
Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.