No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q8_0
All models by JetBrains →This repository contains a GGUF Q8_0 quantization of
JetBrains/Mellum2-12B-A2.5B-Thinking, ready to run with
llama.cpp, Ollama, LM Studio, and
other GGUF-compatible runtimes.
This quantization (Q8_0): 8-bit. Effectively lossless — KL divergence from BF16 is ~0.004 and it keeps BF16's top token 97% of the time (its Wikitext-2 perplexity is even marginally lower than BF16).
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.
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.
The server exposes an OpenAI-compatible API on http://localhost:8080/v1:
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.
hf download JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q8_0 Mellum2-12B-A2.5B-Thinking-Q8_0.gguf --local-dir .# Pull and serve in one step (downloads the GGUF automatically)llama-server -hf JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q8_0 \ --ctx-size 131072 \ --temp 0.6 --top-p 0.95 --top-k 20
# Or run a one-off prompt with a local filellama-cli -m Mellum2-12B-A2.5B-Thinking-Q8_0.gguf \ --ctx-size 131072 \ --temp 0.6 --top-p 0.95 --top-k 20 \ -p "Is 1024 a power of 2? Explain your reasoning."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-Q8_0", 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)ollama run hf.co/JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q8_0