Mellum2.1 — local AI model by JetBrains
Written by Jakub Rusinowski · Last updated
JetBrains' open coding models. Mellum2.1 Thinking is a 12B mixture-of-experts model with 2.5B active parameters, post-trained mostly with reinforcement learning inside real repositories (shell and file-editing tools, rewarded when tests pass), for agentic software engineering and as a sub-agent. Apache 2.0, 131,072-token context. At about 8 GB in Q4_K_M it is one of the few agentic coding models that fits a mid-range laptop.
Variants
The smallest Mellum2.1 variant needs about 9 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| Mellum2.1 12B Thinking → 12B (2.5B active) | ~8.9 GB | 131,072 | cloud-hosted tag |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run Mellum2.1 locally
Install Ollama, then pull the tag.
No Ollama library entry yet. JetBrains' official GGUF files are the local route; the card's own serving recipe is vLLM.
Pick a size above for its own VRAM figure, speed estimate and install command.
Licence
Commercial use permitted. No usage restrictions beyond attribution.
Applies to: Mellum2.1 12B ThinkingRecommended GPU
The cheapest catalogued GPU that runs Mellum2.1 locally (min 9 GB VRAM) is the Intel Arc B570 (10 GB).
Mellum2.1 — frequently asked questions
How much VRAM does Mellum2.1 need?
Mellum2.1 needs about 9 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Mellum2.1 12B Thinking (9 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Mellum2.1 on an RTX 4090 (24 GB)?
Yes — Mellum2.1 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
What quantization should I use for Mellum2.1?
Q4_K_M is the best balance of quality and VRAM for Mellum2.1 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run Mellum2.1 with Ollama?
Mellum2.1 has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.