Mistral Large 2 by Mistral AI — 123B open-weight local LLM. License: Mistral Research. Benchmarks, VRAM requirements per quantization, GPU compatibility, pricing and community reviews on slopsome.com.
Key specs
| Type | Local open-weight |
|---|
| Parameters | 123B total |
|---|
| Architecture | — |
|---|
| Context window | 131K tokens |
|---|
| Knowledge cutoff | — |
|---|
| Modalities | text |
|---|
| Recommended backends | — |
|---|
| Minimum viable rig | — |
|---|
Benchmark scores
| GPQA Diamond | 55% |
|---|
| SWE-bench Verified | 38% |
|---|
| AIME | 55% |
|---|
| MMLU-Pro | 74% |
|---|
| BFCL v3 (tool use) | 82% |
|---|
| Composite score | 15.59 |
|---|
| Community rating | No reviews yet |
|---|
VRAM & disk per quantization
| Quant | VRAM | Disk | RAM | Context |
|---|
| Q4_K_M | 73 GB | 71 GB | 80 GB | 131K |