Qwen3.6-35B-A3B vs Mistral-Large-4-1T-A52B
Specs, VRAM requirements and download trends — updated 10 November 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-35B-A3B | Mistral-Large-4-1T-A52B |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 36.0 B | 52.0 B |
| Architecture | Qwen3_5MoeForConditionalGeneration | MistralLarge4ForConditionalGeneration |
| Context length | 262,144 | 1,048,576 |
| Licence | apache-2.0 | other |
| Commercial use | Allowed | Unknown |
| Languages | — | 39 |
| Downloads 30d | 4,209,694 | 12,060 |
| Downloads all time | 35.1 M | 12 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-15 | 2026-09-30 |
| API input price / 1M tokens | $0.10 | $0.70 |
| API output price / 1M tokens | $0.90 | $2.10 |
| Est. cost per 1M input + 1M output tokens | $1.00 | $2.80 |
| Cached input / 1M tokens | $0.025 | $0.07 |
| AA Intelligence Index | — | 26.1 |
| AA Coding Index | 41.9 | — |
| AA Agentic Index | 13.1 | — |
| Max output tokens | 235,929 | 262,144 |
| API providers | 11 | 1 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen3.6-35B-A3B
$1.00
Mistral-Large-4-1T-A52B
$2.80
Qwen3.6-35B-A3B is 2.8× cheaper at list price.
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
6.0 M278
Qwen3.6-35B-A3B
Mistral-Large-4-1T-A52B
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.6-35B-A3B · fp16
85.0 GB / 24 GB
Mistral-Large-4-1T-A52B · fp16
1,174.9 GB / 24 GB