whatmodel.sh / StarChat2 15B v0.1
StarChat2 15B v0.1
↗ share
+ contribute
StarChat2 15B v0.1 is an open-weights language model from Hugging Face, released March 2024. Its published size is 15.96B parameters and a 16k-token context window.
Catalogue identity notes
Maker repo HuggingFaceH4/starchat2-15b-v0.1 @837a7b6: no licence tag on the card. 15,957,913,600 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-03: month the maker's Hugging Face repo was created (createdAt 2024-03-10).
$ how it compares
The LLMs ranked either side of StarChat2 15B v0.1, out of 828 with a score, then more from Hugging Face.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 449 |  DeepSeek R1 Distill Qwen 7B | 48±1 | local | ||
| 450 |  XwinCoder-34B | 48±1 | local | ||
| 451 | StarChat2 15B v0.1 | 48±1 | local | ||
| 452 |  Code Millenials 34B | 48±1 | local | ||
| 453 |  Reka Core (2024-05-01) | 48±1 | comparison only | ||
| more from Hugging Face | |||||
| 532 | Zephyr ORPO 141B-A35B v0.1 | 45±2 | local | ||
| 577 | SmolLM3 3B | 43±1 | local | ||
| 678 | Zephyr 7B alpha | 36±1 | local | ||
$ what it's good at
coding▁▁▁▃▆██▇▆▄▃▁ #279 of 458 · 100% of its score · 3 tests
Beats Qwen3-VL 32B Instruct, Solar Open 100B (102B-A12B), GLM-4.7-Flash here, though they rank higher overall. Trails DeepSeek LLM 67B Chat, Yi 1.5 9B Chat, Mistral NeMo Instruct (2407) here, though they rank lower overall.
$ where to run it
llama.cpp · recommended
version
- Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.macOS / Linux
curl -LsSf https://llama.app/install.sh | shWindowsirm https://llama.app/install.ps1 | iex - Run StarChat2 15B v0.1 · needs ~9.9 GB · from huggingface.co/mradermacherchat in the terminal
llama cli -hf mradermacher/starchat2-15b-v0.1-GGUF:Q4_K_M - Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf mradermacher/starchat2-15b-v0.1-GGUF:Q4_K_M
LM Studio
version
- Install LM Studio · Open the app once before using the lms command.
- Run StarChat2 15B v0.1 · needs ~9.9 GB · from huggingface.co/mradermacher
- Or download it in the terminal
lms get https://huggingface.co/mradermacher/starchat2-15b-v0.1-GGUF@Q4_K_M -y - Then run lms ls to see its name, and lms chat followed by that name
Ollama
version
- Install Ollama
download it (macOS / Windows) ↗
Linuxcurl -fsSL https://ollama.com/install.sh | sh - Run StarChat2 15B v0.1 · needs ~9.9 GB · from huggingface.co/mradermacherchat in the terminal
ollama run hf.co/mradermacher/starchat2-15b-v0.1-GGUF:Q4_K_M
Other ways to run it
- Run it as published · needs ~31.92 GB · from huggingface.co/HuggingFaceH4
uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='HuggingFaceH4/starchat2-15b-v0.1', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"
Weights and documentation: huggingface.co/HuggingFaceH4 ↗
$ how the score was worked out · EvalPlus / EvalPerf published… 100%
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 |
|---|---|---|
 EvalPlus / EvalPerf published evaluation runs | 3 | 100% |
| prior · pull toward the middle | 0% | |
| weighted average | = 48.2 |
$ 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