Qwen3-8B vs Mistral-Small-24B-Instruct-2501
Specs, VRAM requirements and download trends — updated 24 October 2026.
mistralai · B · Open weights
Params
23.6 B
Context
32,768
30d
74 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-8B | Mistral-Small-24B-Instruct-2501 |
|---|---|---|
| Deployment | Open weights | Open weights · also via API |
| Parameters | 8.2 B | 23.6 B |
| Architecture | Qwen3ForCausalLM | MistralForCausalLM |
| Context length | 40,960 | 32,768 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 10 |
| Downloads 30d | 8,080,572 | 73,988 |
| Downloads all time | 133.5 M | 7.4 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-04-27 | 2025-01-28 |
| API input price / 1M tokens | not on OpenRouter | $0.05 |
| API output price / 1M tokens | not on OpenRouter | $0.08 |
| Est. cost per 1M input + 1M output tokens | not on OpenRouter | $0.13 |
| Cached input / 1M tokens | not on OpenRouter | — |
| AA Intelligence Index | not on OpenRouter | 6.7 |
| AA Coding Index | not on OpenRouter | — |
| AA Agentic Index | not on OpenRouter | — |
| Max output tokens | not on OpenRouter | 16,384 |
| API providers | not on OpenRouter | 1 |
| Tool calling | not on OpenRouter | No |
| Reasoning mode | not on OpenRouter | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Mistral-Small-24B-Instruct-2501
$0.13
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
16.6 M70 K
Qwen3-8B
Mistral-Small-24B-Instruct-2501
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-8B · fp16
19.7 GB / 24 GB
Mistral-Small-24B-Instruct-2501 · fp16
107.8 GB / 24 GB