Mirrored from JetBrains/Mellum2.1-12B-A2.5B-Thinking
All models by JetBrains →[Image blocked: Mellum2.1 benchmarks][!Note] Mellum2.1 is a thinking model. Use it for complex agentic tasks, such as working in a repository, running commands, and calling tools, and for hard non-agentic problems in coding, math, and reasoning.
Mellum2.1 is the next version of Mellum2 Thinking. The architecture is unchanged (a 12B mixture-of-experts model with 2.5B active parameters), and almost all of the work for this version went into post-training, primarily reinforcement learning (RL):
As a result, Mellum2.1 handles agentic tasks much better than Mellum2. After millions of sandboxed runs in real environments during training, it explores a codebase, edits files, and checks its own changes.
Mellum2.1 Thinking has the following features:
GGUF builds for llama.cpp, Ollama, and LM Studio, as well as the multi-token prediction (MTP) head for speculative decoding in vLLM, are coming soon.
All values are percentages; higher is better except HarmBench, where lower is better. All models were evaluated by JetBrains with the same pipeline in thinking mode. All values are self-reported by JetBrains.
Notes:
Released under the Apache 2.0 license.
# Without tool callingvllm serve JetBrains/Mellum2.1-12B-A2.5B-Thinking \ --max-model-len 131072 \ --reasoning-parser qwen3
# With tool callingvllm serve JetBrains/Mellum2.1-12B-A2.5B-Thinking \ --max-model-len 131072 \ --reasoning-parser qwen3 \ --enable-auto-tool-choice \ --tool-call-parser hermesfrom openai import OpenAI# Configured by environment variablesclient = OpenAI()
messages = [ {"role": "user", "content": "Find the bug in this function and explain the fix: def mean(xs): return sum(xs) / len(xs) - 1"},]
chat_response = client.chat.completions.create( model="JetBrains/Mellum2.1-12B-A2.5B-Thinking", messages=messages, max_tokens=81920, temperature=0.6, top_p=0.95, extra_body={"top_k": 20},)print("Chat response:", chat_response)