Prompt: (raw) (yaml)
words:1 bytes:3
Output: llama3.1:8b-instruct-q4_1 (raw)
Stats (raw) | |
Words | 17 |
Bytes | 83 |
Total duration | 1.698175417s |
Load duration | 32.823375ms |
Prompt eval count | 11 token(s) |
Prompt eval duration | 415.571292ms |
Prompt eval rate | 26.47 tokens/s |
Eval count | 21 token(s) |
Eval duration | 1.249219541s |
Eval rate | 16.81 tokens/s |
Model (raw) | |
Name | llama3.1:8b-instruct-q4_1 |
Architecture | llama |
Size | 8.8 GB |
Parameters | 8.0B |
Context length | 131072 |
Embedding length | 4096 |
Quantization | Q4_1 |
Capabilities | completion tools |
System | |
Ollama proc | 100% GPU |
Ollama context | 16384 |
Ollama version | 0.9.7-rc0 |
Multirun timeout | 300 seconds |
Sys arch | arm64 |
Sys processor | arm |
sys memory | 13G + 481M |
Sys OS | Darwin 24.5.0 |