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 in the Mellum family. 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.
Doesn't fit a 24 GB GPU
Smallest consumer fit → Snapdragon X Elite Copilot+ PC · BF16 · 24.8 GB · ~17 tok/s
Macs from 32 GB (BF16 · ~43 tok/s)
Apache 2.0
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Mellum2 12B A2.5B Base Pretrain
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve JetBrains/Mellum2-12B-A2.5B-Base-Pretrain --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX PRO 4500 (32 GB) (7 GB headroom) · BF16
- Generation speed
- ~100 tok/s
- generation speed
- Cost per 1M output tokens
- $0.95
- per 1M output tokens
How Much VRAM Does Mellum2 12B A2.5B Base Pretrain Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 24.7 GB | 24.9 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 24.8 GB |
Selected BF16
Brain floating point 1624.8GBat 16K context
- Weights
- 24.3 GB
- KV cache
- 0.2 GB
- Overhead
- 0.3 GB
Doesn't fit RTX 4090 (reference) · needs 0.8 GB more
Which Hardware 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 1.0 GB, bringing total usage to 25.7 GB. 1 GPU can run it, including NVIDIA GeForce RTX 5090. 98 devices with unified memory can run Mellum2 12B A2.5B Base Pretrain, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M5 Max (36 GB).
32–40 GB
fits · 7.2 GB free · up to 128K ctx
1 GPU · 3 Mac classes · 2 device families
RTX 5090~173Simulate output on RTX 5090M5 Max36 GB~48Simulate output on Mac Studio M5 Max (36 GB)M532 GB~19Simulate output on MacBook Air 13" M5 (32 GB)Orin~26Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~17Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Alternatives to Mellum2 12B A2.5B Base Pretrain
Mellum family · 8 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Gemma 3 12B ITGoogle | 74.2 | 10.9 GB | ~82 | same size |
| Gemma 4 12BGoogle | — | 9 GB | ~80 | same size |
| Mistral Nemo Base 2407Mistral AI | — | 11 GB | ~81 | same size |
| Baichuan2 13B Basebaichuan-inc | — | 11.5 GB | ~76 | same size |
| Llama 2 13B Chat HFMeta | — | 11.5 GB | ~76 | same size |
| Vicuna 13B V1.3LMSYS | — | 8.6 GB | ~76 | same size |
Specifications
- Publisher
- JetBrains
- Family
- Mellum
- Parameters
- 12.1B
- Active parameters
- 2.4B per token
- Architecture
- MellumForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 98,304
- Release Date
- 2026-04-07
- License
- Apache 2.0
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 1.0 GB (25.7 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)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 1.4 GB (at full 131K context)
VRAM usage by quantization
Can I run Mellum2 12B A2.5B Base Pretrain on a Mac?
Yes — Mac Studio M1 Max (32 GB) and 84 other Macs can run Mellum2 12B A2.5B Base Pretrain. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 24.7 GB of usable unified memory (RAM minus macOS overhead).
Can I run Mellum2 12B A2.5B Base Pretrain locally?
Yes — Mellum2 12B A2.5B Base Pretrain can run locally on consumer hardware. 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 ~151 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 5.0 GB active ÷ (8000 × 0.65) = 0.952 ms, plus 28 layers × 0.055 ms = 1.540 ms, so 1000 ÷ 2.492 ms = ~401 tok/s
Estimated speed at BF16 (24.7 GB)
Real-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. Top options include NVIDIA GeForce RTX 5090.
Which devices can run Mellum2 12B A2.5B Base Pretrain?
98 devices with unified memory can run Mellum2 12B A2.5B Base Pretrain at BF16 (24.7 GB), including ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB), GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.