← All modelsMODEL CHECK

Can I run Devstral 2 123B?

Devstral 2 123B by Mistral AI needs around 96 GB of RAM at the recommended 4-bit quantization (74.6 GB download). Your hardware is checked below — instantly, nothing leaves your browser. Expect roughly ~5 tok/s on a Apple M-series Max.

Reading your hardware signals…

Specifications

Parameters123B
Context window256K tokens
ProviderMistral AI
LicenseModified MIT
Released2025-12
Best forCoding

Size by quantization

QuantizationBits/weightDownloadMin RAMQuality
Q2_K3.3551.5 GB96 GBNoticeable loss
Q4_K_MRecommended4.8574.6 GB96 GBRecommended
Q5_K_M5.6586.9 GB128 GBHigh
Q8_08.5130.7 GB192 GBNear-original
F1616246.0 GB256 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~1.8 GB~76.4 GB
8K tokens~3.6 GB~78.2 GB
32K tokens~14.3 GB~88.9 GB
128K tokens~57.4 GB~132.0 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/sWon't fit in VRAM
NVIDIA RTX 4090 24GB1008 GB/sWon't fit in VRAM
Apple M-series (base)100 GB/s~1 tok/s
Apple M-series Pro270 GB/s~3 tok/s
Apple M-series Max410 GB/s~5 tok/s
CPU only (dual-channel DDR5)60 GB/s~1 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.

Run it locally

The easiest path is Ollama — one command and you're chatting:

ollama run devstral-2:123b

Frequently asked questions