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
Size by quantization
| Quantization | Bits/weight | Download | Min RAM | Quality |
|---|---|---|---|---|
| Q2_K | 3.35 | 51.5 GB | 96 GB | Noticeable loss |
| Q4_K_MRecommended | 4.85 | 74.6 GB | 96 GB | Recommended |
| Q5_K_M | 5.65 | 86.9 GB | 128 GB | High |
| Q8_0 | 8.5 | 130.7 GB | 192 GB | Near-original |
| F16 | 16 | 246.0 GB | 256 GB | Original |
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
| Context | KV 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
| Hardware | Bandwidth | ~Speed |
|---|---|---|
| NVIDIA RTX 3060 12GB | 360 GB/s | Won't fit in VRAM |
| NVIDIA RTX 4090 24GB | 1008 GB/s | Won't fit in VRAM |
| Apple M-series (base) | 100 GB/s | ~1 tok/s |
| Apple M-series Pro | 270 GB/s | ~3 tok/s |
| Apple M-series Max | 410 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