Mellum2 12B A2.5B Base Pretrain — Hardware Requirements & GPU Compatibility
Chat
Mellum2 12B A2.5B Base Pretrain is a 12.1B-parameter open language model from JetBrains. It supports a context window of up to 131,072 tokens. At BF16 it needs about 24.67 GB of VRAM — see which GPUs and Macs can run it below.
181 downloads
8 likesSpecifications
- Publisher
- JetBrains
- Parameters
- 12.1B
- Architecture
- MellumForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 98,304
- Release Date
- 2026-06-01
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Mellum2 12B A2.5B Base Pretrain Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 24.7 GB | 28.8 GB | 24.30 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Mellum2 12B A2.5B Base Pretrain?
BF16 · 24.7 GBMellum2 12B A2.5B Base Pretrain (BF16) requires 24.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 33+ GB is recommended. Using the full 131K context window can add up to 4.2 GB, bringing total usage to 28.8 GB. 1 GPU can run it, including NVIDIA GeForce RTX 5090.
All compatible consumer-level GPUs are running near their VRAM limit. You may also want to consider professional GPUs (e.g., NVIDIA A100, H100) which offer significantly more VRAM. For more headroom and better throughput, consider a multi-GPU configuration with tensor parallelism (supported by tools like vLLM, llama.cpp, or text-generation-inference).
Decent
— Enough VRAM, may be tightWhich Devices Can Run Mellum2 12B A2.5B Base Pretrain?
BF16 · 24.7 GB15 devices with unified memory can run Mellum2 12B A2.5B Base Pretrain, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio M4 Max (36 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does Mellum2 12B A2.5B Base Pretrain need?
Mellum2 12B A2.5B Base Pretrain requires 24.7 GB of VRAM at BF16. Full 131K context adds up to 4.2 GB (28.8 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 12.1B × 16 bits ÷ 8 = 24.3 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 4.5 GB (at full 131K context)
VRAM usage by quantization
BF1624.7 GBBF16 + full context28.8 GB- Can I run Mellum2 12B A2.5B Base Pretrain on a Mac?
Mellum2 12B A2.5B Base Pretrain requires at least 24.7 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Mellum2 12B A2.5B Base Pretrain locally?
Yes — Mellum2 12B A2.5B Base Pretrain can run locally on consumer hardware. At BF16 quantization it needs 24.7 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Mellum2 12B A2.5B Base Pretrain?
At BF16, Mellum2 12B A2.5B Base Pretrain can reach ~118 tok/s on AMD Instinct MI300X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 24.7 × 0.55 = ~118 tok/s
Estimated speed at BF16 (24.7 GB)
~118 tok/s~88 tok/s~73 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Mellum2 12B A2.5B Base Pretrain?
At BF16, the download is about 24.30 GB.
- Which GPUs can run Mellum2 12B A2.5B Base Pretrain?
1 consumer GPU can run Mellum2 12B A2.5B Base Pretrain at BF16 (24.7 GB). Top options include NVIDIA GeForce RTX 5090.
- Which devices can run Mellum2 12B A2.5B Base Pretrain?
15 devices with unified memory can run Mellum2 12B A2.5B Base Pretrain at BF16 (24.7 GB), including Mac Mini M4 (32 GB), Mac Mini M4 Pro (48 GB), Mac Pro M2 Ultra (192 GB), Mac Studio M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.