whatmodel.sh / Llama-3-8B-Instruct-RainbowPO
Llama-3-8B-Instruct-RainbowPO
↗ share
+ contribute
Llama-3-8B-Instruct-RainbowPO is an open-weights language model from BraceZHY (RainbowPO), released October 2024. Its published size is 8.03B parameters. Licence: mit.
Catalogue identity notes
Maker repo BraceZHY/Llama-3-8B-Instruct-RainbowPO @abda6ce: licence tag mit. 8,030,261,248 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-10: month the maker's Hugging Face repo was created (createdAt 2024-10-31). Gated repository (licence acceptance required on Hugging Face).
$ how it compares
The LLMs ranked either side of Llama-3-8B-Instruct-RainbowPO, out of 1132 with a score.
| # | model | score | where |
|---|---|---|---|
| 426 |  Command A Reasoning (08-2025) | 55±2 | local |
| 427 |  Bielik 11B v3.0 Instruct | 55±2 | local |
| 428 | Llama-3-8B-Instruct-RainbowPO | 55±2 | local |
| 429 |  Olmo 3.1 32B Instruct | 55±2 | local |
| 430 |  ToolACE-8B | 55±6 | local |
$ what it's good at
chat & writing▁▁▁▄▆▅▆█▆▆▆▂ #222 of 466 * · 99% of its score · 1 test
Beats Granite 4.2 8B, Qwen3-VL 30B-A3B Thinking, Mistral Small 4 (119B-A6.5B) here, though they rank higher overall. Trails LFM2.5 1.2B Instruct, Granite 4.0 H Micro 3B, Gemma 3n E4B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| AlpacaEval 2 length-controlled | 51.7% ✎ | ▁▂▂▃▆▆█▆▄▄▁▁ beats 108/122 | 99% |
$ where to run it
Other ways to run it
- Run it as published · needs ~16.06 GB · from huggingface.co/BraceZHY (official)
uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='BraceZHY/Llama-3-8B-Instruct-RainbowPO', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"
Official weights and documentation: huggingface.co/BraceZHY ↗
$ how the score was worked out · AlpacaEval 1.0 and 2.0 leader… 99%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository) | 1 | 99% |
| prior · pull toward the middle | 1% | |
| weighted average | = 54.8 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json