← All modelsMODEL CHECK

Can I run Mellum 2 12B-A2.5B?

Mellum 2 12B-A2.5B by JetBrains needs around 12 GB of RAM at the recommended 4-bit quantization (7.3 GB download). Your hardware is checked below — instantly, nothing leaves your browser. Expect roughly ~202 tok/s on a NVIDIA RTX 3060 12GB.

Reading your hardware signals…

Specifications

Parameters12B (2.5B active)
Context window128K tokens
ProviderJetBrains
LicenseApache 2.0
Released2026-06
Best forCoding

Size by quantization

QuantizationBits/weightDownloadMin RAMQuality
Q2_K3.355.0 GB8 GBNoticeable loss
Q4_K_MRecommended4.857.3 GB12 GBRecommended
Q5_K_M5.658.5 GB16 GBHigh
Q8_08.512.8 GB24 GBNear-original
F161624.0 GB32 GBOriginal

Sizes are estimates from parameter count × bits per weight; real GGUF builds vary slightly. · Data updated: 2026-06-11 · How we calculate these numbers →

Memory needed by context length

ContextKV cache (est.)Total memory (Q4)
4K tokens~0.6 GB~7.9 GB
8K tokens~1.3 GB~8.6 GB
32K tokens~5.0 GB~12.3 GB
128K tokens~20.1 GB~27.4 GB

The KV cache grows with context length — a model that fits at 4K can run out of memory at 32K. Estimates assume an FP16 cache with grouped-query attention; actual usage varies by runtime.

Estimated speed by hardware

HardwareBandwidth~Speed
NVIDIA RTX 3060 12GB360 GB/s~202 tok/s
NVIDIA RTX 4090 24GB1008 GB/s~565 tok/s
Apple M-series (base)100 GB/s~56 tok/s
Apple M-series Pro270 GB/s~151 tok/s
Apple M-series Max410 GB/s~230 tok/s
CPU only (dual-channel DDR5)60 GB/s~34 tok/s

Token generation is memory-bandwidth bound: tok/s ≈ bandwidth × 0.85 ÷ model size at Q4. Real-world numbers vary by runtime and context length.

Frequently asked questions