Mixtral 8x7B by Mistral AI — 46.7B MoE (12.9B active) open-weight local LLM. License: Apache-2.0. Benchmarks, VRAM requirements per quantization, GPU compatibility, pricing and community reviews on slopsome.com.
Key specs
| Type | Local open-weight |
|---|
| Parameters | 46.7B total · MoE, 12.9B active |
|---|
| Architecture | — |
|---|
| Context window | 33K tokens |
|---|
| Knowledge cutoff | — |
|---|
| Modalities | text |
|---|
| Recommended backends | — |
|---|
| Minimum viable rig | — |
|---|
Benchmark scores
| GPQA Diamond | 38% |
|---|
| SWE-bench Verified | 18% |
|---|
| AIME | 28% |
|---|
| MMLU-Pro | 56% |
|---|
| BFCL v3 (tool use) | 64% |
|---|
| Composite score | 13.03 |
|---|
| Community rating | No reviews yet |
|---|
VRAM & disk per quantization
| Quant | VRAM | Disk | RAM | Context |
|---|
| Q4_K_M | 28 GB | 27 GB | 32 GB | 33K |