What GPU do I need to run JetBrains/Mellum2-12B-A2.5B-Base?
12.1B parameters, published in BF16. View on Hugging Face
Mellum2-12B-A2.5B-Base is published by JetBrains on Hugging Face, with 17,383 downloads and 24 likes to date. It's a MellumForCausalLM model built for text-generation, published natively in BF16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 22.6 GB | 27.2 GB | RTX A6000 | 1 | $0.363/hr |
| cheaper alt. | RTX 3060 | 3 | $0.330/hr | ||
| FP8 (quantized) | 11.3 GB | 13.6 GB | RTX 5060 Ti | 1 | $0.180/hr |
| INT4 (quantized) | 5.7 GB | 6.8 GB | RTX 3070 | 1 | $0.088/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run Mellum2-12B-A2.5B-Base at its published (BF16) precision: 1× RTX A6000, at $0.363/hr per GPU ($0.363/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Mellum2-12B-A2.5B-Base: KV cache by context length
The KV cache is the memory the attention layers hold for every token of context, on top of the weights. It is not part of the flat 1.2x overhead in the table above, grows with context length and with every concurrent request, and is why a long-context deployment needs more VRAM than the table shows.
Sliding-window attention: windowed layers stop growing at the window, the full-attention layers keep growing. Cached per token: 57,344 bytes at 16-bit while the context is inside the window.
| Context | KV cache, one sequence |
|---|---|
| 4K | 0.10 GB |
| 32K | 0.48 GB |
| 128K | 1.8 GB |
Computed from the layer, head and window counts in the model's own configuration (JetBrains/Mellum2-12B-A2.5B-Base), at 16 bits per cached value. Each concurrent sequence needs its own cache, on top of the weights.
Mellum2-12B-A2.5B-Base: common questions
Does Mellum2-12B-A2.5B-Base fit on a 32 GB GPU?
Yes. At BF16 it needs 27.2 GB of VRAM, so a 32 GB card holds it with 4.8 GB to spare. A 24 GB card is not enough for it at BF16.
What is the least VRAM Mellum2-12B-A2.5B-Base can run in?
6.8 GB, at INT4 (quantized), which fits an 8 GB card, against 27.2 GB at BF16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Does quantizing Mellum2-12B-A2.5B-Base lower the GPU bill?
Yes. At BF16 the cheapest live fit is one RTX A6000 at $0.363/hr. At INT4 (quantized) it drops to one RTX 3070 at $0.088/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
Alternatives at this size
Other models for text-generation within about a third of Mellum2-12B-A2.5B-Base's 12.1B parameters, from other model lines.
- Qwen3-8B (8.2B, BF16)
- granite-4.1-8b (8.8B, BF16)
- DeepSeek-R1-0528-Qwen3-8B (8.2B, BF16)
- gemma-2-9b-it (9.2B, BF16)
- phi-4 (14.7B, BF16)
More on Mellum2-12B-A2.5B-Base
Fits on a 32 GB GPU at BF16: every model that fits in 32 GB.
Fits on a 16 GB GPU at FP8: every model that fits in 16 GB.
Fits on an 8 GB GPU at INT4: every model that fits in 8 GB.
Related reading: RTX A6000 pricing and specs, How much VRAM you need for LLMs, Serving LLMs with vLLM, vLLM vs TensorRT-LLM vs SGLang, and Best GPU for LLM inference.
Your own GPU cloud accounts
One console for the GPU clouds you already rent from. Your keys stay on your machine.
$20 a month, flat