New Report bugs or version requests.

Note: It has NVIDIA as its name; from training pipelines/distillation are baked into the weights - dev is JetBrains. Neat model. The import contains suggested parameters.

Imported from: https://huggingface.co/JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M

Mellum2 Thinking — GGUF (Q4_K_M)

This repository contains a GGUF Q4_K_M quantization of JetBrains/Mellum2-12B-A2.5B-Thinking, ready to run with llama.cpp, Ollama, LM Studio, and other GGUF-compatible runtimes.

This quantization (Q4_K_M): 4-bit k-quant (medium). Strong quality/size trade-off (KLD ~0.052, 90% top-token agreement) — a good default. File Size Mellum2-12B-A2.5B-Thinking-Q4_K_M.gguf 8.1 GB

Mellum 2 Thinking is a Mixture-of-Experts reasoning model (64 experts, 8 activated per token, 131,072-token context) that emits its chain of thought inside <think>...</think> blocks before the final answer.

For the full model description, evaluation results, and architecture details, see the original model card: JetBrains/Mellum2-12B-A2.5B-Thinking.

Quantization Description Size KLD vs BF16 ↓ Top-token match ↑ BF16 ) 24.3 GB — —

Q4_K_M 8.1 GB 0.052 89.8%

KL divergence and top-token agreement are measured against the BF16 logits on Wikitext-2 (n_ctx=512); lower KLD / higher agreement means closer to the unquantized model. Download

hf download JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M Mellum2-12B-A2.5B-Thinking-Q4_K_M.gguf –local-dir .

Run with llama.cpp

# Pull and serve in one step (downloads the GGUF automatically)
llama-server -hf JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M \
  --ctx-size 131072 \
  --temp 0.6 --top-p 0.95 --top-k 20

# Or run a one-off prompt with a local file
llama-cli -m Mellum2-12B-A2.5B-Thinking-Q4_K_M.gguf \
  --ctx-size 131072 \
  --temp 0.6 --top-p 0.95 --top-k 20 \
  -p "Is 1024 a power of 2? Explain your reasoning."

The server exposes an OpenAI-compatible API on http://localhost:8080/v1:

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8080/v1", api_key="llama.cpp")

chat_response = client.chat.completions.create(
    model="JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M",
    messages=[
        {"role": "user", "content": "Is 1024 a power of 2? Explain your reasoning."},
    ],
    max_tokens=81920,
    temperature=0.6,
    top_p=0.95,
    extra_body={"top_k": 20},
)
print(chat_response.choices[0].message.content)

Run with Ollama

ollama run hf.co/JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M

License

Released under the Apache 2.0 license.

For the full model card, evaluation results, and architecture details, refer to the original model: JetBrains/Mellum2-12B-A2.5B-Thinking.