mradermacher

/

model_requests

like 147

It's queued!

You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#EuroLLM-22B-Instruct-2512-FT-GGUF for quants to appear.

"num_fewshot": 0,
"gsm8k": {
"alias": "gsm8k",
"exact_match,strict-match": 0.42,
"exact_match_stderr,strict-match": 0.049604496374885836,
"exact_match,flexible-extract": 0.52,
"exact_match_stderr,flexible-extract": 0.050211673156867795
}
"eurollm-22b-instruct-2512-ft@q4_k",
"system_instruction": "You are a helpful assistant. Solve the math problem step by step. You must always end your response with the final numerical answer preceded by four hashtags, like this: #### 42",
"limit": 100.0,

I did a very simple test, and your gguf is excellent. I tested a regular model, and it already surpasses Qwen3 30B A3B. Beautifully done.

Thank you =)