Views
No views yet
internlm/Intern-S2-Preview.1python -m mlx_lm generate \
2 --model <namespace>/Intern-S2-Preview-FP8-MLX-4bit \
3 --trust-remote-code \
4 --prompt "Write a concise response to your prompt here." \
5 --max-tokens 40961python -m mlx_lm generate \
2 --model /path/to/Intern-S2-Preview-FP8-MLX-4bit \
3 --trust-remote-code \
4 --prompt "Write a concise response to your prompt here." \
5 --max-tokens 4096mlx_lm generate on Apple Silicon.1python -m mlx_lm generate \
2 --model /path/to/Intern-S2-Preview-FP8-MLX-4bit \
3 --trust-remote-code \
4 --prompt "Write a concise response to your prompt here." \
5 --max-tokens 4096| Metric | Value |
|---|---|
| Prompt tokens | 19 |
| Prompt throughput | 306.835 tokens/sec |
| Generation tokens | 702 |
| Generation throughput | 123.388 tokens/sec |
| Peak memory | 19.651 GB |
1python -m mlx_lm generate \
2 --model /path/to/Intern-S2-Preview-FP8-MLX-4bit \
3 --trust-remote-code \
4 --prompt "Do not show reasoning, analysis, thinking process, scratchpad, or <think> text. Output only the final answer. Write a concise response to your prompt here." \
5 --max-tokens 4096| Metric | Value |
|---|---|
| Prompt tokens | 44 |
| Prompt throughput | 487.095 tokens/sec |
| Generation tokens | 817 |
| Generation throughput | 122.650 tokens/sec |
| Peak memory | 19.695 GB |
safetensorsinternlm/Intern-S2-Previewinternlm/Intern-S2-Preview. Refer to the base model repository for upstream license and usage terms.