Model Detail
Mellum2-12B-A2.5B-Claude-4.6-4.8-Opus-Thinking-GGUF
—Mellum2-12B-A2.5B-Claude-4.6-4.8-Opus-Thinking-GGUF is a code generation model with 12B parameters released by yuxinlu1. The model is registered under the text-generation pipeline tag on Hugging Face, distributed under the permissive apache-2.0 license.
Mellum2-12B-A2.5B-Claude-4.6-4.8-Opus-Thinking-GGUF ships with 12B parameters, distributed as a quantized weight variant for lower-VRAM inference. The apache-2.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
Mellum2-12B-A2.5B-Claude-4.6-4.8-Opus-Thinking-GGUF is best fit for code completion, repository-scale Q&A, and pair-programming integrations. It is a less obvious choice for one-shot generation of security-critical code without review. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains
Mellum2 Technical Report
arXiv:2605.31268v1 Announce Type: new Abstract: We present Mellum 2, an open-weight 12B-parameter Mixture-of-Experts (MoE) language model with 2.5B active parameters per token. Mellum 2 is a general-purpose language model specialized in software engineering, spanning code generation and editing, deb
