Open-weight LLM comparison
Mixtral 8x22B vs Qwen 2.5 72B
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 | Mixtral 8x22B | Qwen 2.5 72B |
|---|---|---|
| Total parameters | 141 B | 72 B |
| Active parameters (MoE) | 39 B | — |
| Architecture | MoE (141B total, 39B active per token) | dense |
| Vendor | Mistral AI | Alibaba |
| License | Apache 2.0 | Qwen License (72B only) |
| Released | 2024-04-17 | 2024-09-19 |
| Weights @ FP16 | 282 GB | 144 GB |
| Weights @ INT8 | 141 GB | 72 GB |
| Weights @ INT4 | 71 GB | 36 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 | Mixtral 8x22B | Qwen 2.5 72B |
|---|---|---|
| MMLU (5-shot) | 77.8 | 86.1 |
| HumanEval | 76.2 | 86.6 |
| MATH (maj@4) | 41.8 | not published |
| MATH (0-shot) | not published | 83.1 |
| GPQA | not published | 49.0 |
Sources: Mixtral 8x22B model card · Qwen 2.5 72B 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
Mixtral 8x22B vs Qwen 2.5 72B: which is bigger?
Mixtral 8x22B has more parameters (Mixtral 8x22B: 141 B; Qwen 2.5 72B: 72 B). More parameters usually means higher ceiling on capability and higher memory requirement, though MoE architectures decouple total parameters from per-token compute.
Mixtral 8x22B vs Qwen 2.5 72B: which is newer?
Qwen 2.5 72B released 2024-09-19; Mixtral 8x22B released 2024-04-17.
Mixtral 8x22B vs Qwen 2.5 72B: which needs less memory to serve?
Qwen 2.5 72B needs less HBM. Weights-only footprint at FP16: Mixtral 8x22B 282 GB; Qwen 2.5 72B 144 GB. Half those numbers at INT8, quarter at INT4. Real serving adds 10-30% for KV cache.
Mixtral 8x22B vs Qwen 2.5 72B: which license is more permissive?
Mixtral 8x22B: Apache 2.0. Qwen 2.5 72B: Qwen License (72B only). 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 · Mixtral 8x22B full page · Qwen 2.5 72B full page.