Open-weight LLM comparison
Command R+ vs Mixtral 8x22B
Side-by-side
Straight from each model's release page and Hugging Face card. Memory shown is for the weights alone: add roughly 15% for real serving. Bold column marks the more parameters and the smaller memory footprint.
| Field | Command R+ | Mixtral 8x22B |
|---|---|---|
| Total parameters | 104 B | 141 B |
| Active parameters (MoE) | — | 39 B |
| Architecture | dense | MoE (141B total, 39B active per token) |
| Vendor | Cohere | Mistral AI |
| License | CC-BY-NC-4.0 (non-commercial) | Apache 2.0 |
| Released | 2024-04-04 | 2024-04-17 |
| Weights @ FP16 | 208 GB | 282 GB |
| Weights @ INT8 | 104 GB | 141 GB |
| Weights @ INT4 | 52 GB | 71 GB |
Which is smarter (published benchmarks)
Vendor-reported quality scores on the standard leaderboards. Bold column marks the higher score on the same test.
| Benchmark | Command R+ | Mixtral 8x22B |
|---|---|---|
| MMLU (5-shot) | 75.7 | 77.8 |
| HumanEval | 70.7 | 76.2 |
| MATH (maj@4) | not published | 41.8 |
Sources: Command R+ model card · Mixtral 8x22B model card. Benchmark methodology and prompt template can shift these numbers by several points, so treat these as relative rankings, not absolute scores.
Common questions
Command R+ vs Mixtral 8x22B: which is bigger?
Mixtral 8x22B has more parameters (Command R+: 104 B; Mixtral 8x22B: 141 B). More parameters usually means higher ceiling on capability and higher memory requirement, though MoE architectures decouple total parameters from per-token compute.
Command R+ vs Mixtral 8x22B: which is newer?
Mixtral 8x22B released 2024-04-17; Command R+ released 2024-04-04.
Command R+ vs Mixtral 8x22B: which needs less memory to serve?
Command R+ needs less HBM. Weights-only footprint at FP16: Command R+ 208 GB; Mixtral 8x22B 282 GB. Half those numbers at INT8, quarter at INT4. Real serving adds 10-30% for KV cache.
Command R+ vs Mixtral 8x22B: which license is more permissive?
Command R+: CC-BY-NC-4.0 (non-commercial). Mixtral 8x22B: Apache 2.0. Apache 2.0 and MIT allow unrestricted commercial use; Llama Community License allows commercial use but restricts training larger models on outputs; CC-BY-NC and vendor-specific licenses (Qwen 72B, Gemma) have narrower terms. Check the model card for the exact clauses.
See also: every LLM comparison · Command R+ full page · Mixtral 8x22B full page.