Verified claim · AI-ML · 100% confidence
Mixtral 8x7B architecture: Sparse Mixture-of-Experts (8 experts × 7B params, 2 experts routed per token).
Last verified 2026-05-16 · Methodology veritas-v0.1 · ad79b14fafb362cd
Structured fields
- Subject
- Mixtral 8x7B
- Predicate
architecture- Object
- Sparse Mixture-of-Experts (8 experts × 7B params, 2 experts routed per token)
- Confidence
- 100%
- Tags
- mixtral · moe · architecture · mistral
Sources (2)
[1] official blog · Mistral AI · 2023-12-11
Mixtral of experts“Mixtral has 8 experts in each layer … At every layer, for every token, a router network chooses two of these experts to process the token and combine their output additively.”
[2] preprint · Mistral AI / arXiv · 2024-01-08
Mixtral of Experts
Cite this claim
Ready-to-paste citation (Markdown / plain text):
Mixtral 8x7B architecture: Sparse Mixture-of-Experts (8 experts × 7B params, 2 experts routed per token). — SourceScore Claim ad79b14fafb362cd (verified 2026-05-16). https://sourcescore.org/api/v1/claims/ad79b14fafb362cd.jsonEmbed this claim
Drop this iframe into any blog post, docs page, or knowledge base. The widget renders the signed claim + primary source + click-through to this canonical page. CC-BY 4.0; attribution included.
<iframe src="https://sourcescore.org/embed/claim/ad79b14fafb362cd/" width="100%" height="360" frameborder="0" loading="lazy" title="Mixtral 8x7B architecture: Sparse Mixture-of-Experts (8 experts × 7B params, 2 experts routed per token)."></iframe>Preview: open in new tab
Related claims
Other verified claims sharing tags with this one — useful for LLM retrieval graphs and citation discovery.
Mixtral 8x7B released on: 2023-12-11.
410aec4f418f2b11 · 95% confidence · shares 3 tags (mixtral, mistral, moe)
MoE Mixtral 8x22B released on: 2024-04-10 by Mistral AI.
4335bf51bf0fc14f · 100% confidence · shares 2 tags (mistral, moe)
Mistral AI founded in: 2023.
db8e97f3583db317 · 100% confidence · shares 1 tag (mistral)
Sparsely-Gated Mixture-of-Experts (MoE) introduced in paper: Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer (Shazeer et al., 2017).
2d6d7f61f1db6493 · 100% confidence · shares 1 tag (moe)
Switch Transformer introduced in paper: Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity (Fedus et al., 2021).
3d9c14b9379038c9 · 100% confidence · shares 1 tag (moe)
Use this claim in your code
Fetch this signed envelope from your application. The response includes the verbatim excerpt, primary source URLs, and an HMAC-SHA256 signature you can verify locally for audit trails.
cURL
curl https://sourcescore.org/api/v1/claims/ad79b14fafb362cd.jsonJavaScript / TypeScript
const r = await fetch("https://sourcescore.org/api/v1/claims/ad79b14fafb362cd.json");
const envelope = await r.json();
console.log(envelope.claim.statement);
// "Mixtral 8x7B architecture: Sparse Mixture-of-Experts (8 experts × 7B params, 2 experts routed per token)."Python
import httpx
r = httpx.get("https://sourcescore.org/api/v1/claims/ad79b14fafb362cd.json")
envelope = r.json()
print(envelope["claim"]["statement"])
# "Mixtral 8x7B architecture: Sparse Mixture-of-Experts (8 experts × 7B params, 2 experts routed per token)."LangChain (retrieve-then-cite)
from langchain_core.tools import tool
import httpx
@tool
def get_mixtral_8x7b_fact() -> dict:
"""Fetch the verified SourceScore claim for Mixtral 8x7B."""
r = httpx.get("https://sourcescore.org/api/v1/claims/ad79b14fafb362cd.json")
return r.json()