Model comparison
Mixtral 8x7B v0.1 vs Mixtral 8x22B
Capability radar, value bars, and side-by-side posture.
Mixtral 8x7B v0.1
Not scored
value score
Mixtral 8x22B
76
value score
Mixtral 8x7B v0.1 ctx
—
Mixtral 8x22B ctx
66K
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- Mixtral 8x22B76
Attribute tape
| Field | Mixtral 8x7B v0.1 | Mixtral 8x22B |
|---|---|---|
| Developer | Mistral AI | Mistral AI |
| Context | — | 66K |
| Modalities | Text, Code | |
| Openness | — | Open Weights |
| Speed | — | — |
| Price | — | — |
| Value score | — | 76 |
| Summary | Mixtral 8x7B v0.1 is Mistral AI's open-weight base large language model built on a sparse Mixture-of-Experts (MoE) architecture, routing each token through 2 of 8 experts for roughly 46B total parameters but only ~12.9B active per token. It is a decoder-only text generation model released under the Apache 2.0 license. | Sparse MoE open-weights Mixtral. |