Qwen3-30B-A3B vs Meta-Llama-3-8B
Specs, VRAM requirements and download trends — updated 5 August 2026.
Qwen · A · Open weights
Params
30.5 B
Context
40,960
30d
1.0 M
apache-2.0 · commercial OK
meta-llama · B · Open weights
Params
8.0 B
Context
—
30d
139 K
llama3 licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-30B-A3B | Meta-Llama-3-8B |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 30.5 B | 8.0 B |
| Architecture | Qwen3MoeForCausalLM | LlamaForCausalLM |
| Context length | 40,960 | — |
| Licence | apache-2.0 | llama3 |
| Commercial use | Allowed | Conditional |
| Languages | — | 1 |
| Downloads 30d | 1,005,143 | 139,310 |
| Downloads all time | 22.5 M | 47.3 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | Yes — accept licence |
| First seen on the Hub | 2025-04-27 | 2024-04-17 |
| API input price / 1M tokens | $0.12 | not on OpenRouter |
| API output price / 1M tokens | $0.50 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $0.62 | not on OpenRouter |
| Cached input / 1M tokens | — | not on OpenRouter |
| AA Intelligence Index | 7.6 | not on OpenRouter |
| AA Coding Index | — | not on OpenRouter |
| AA Agentic Index | — | not on OpenRouter |
| Max output tokens | 16,384 | not on OpenRouter |
| API providers | 1 | not on OpenRouter |
| Tool calling | Yes | not on OpenRouter |
| Reasoning mode | Yes | not on OpenRouter |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen3-30B-A3B
$0.62
Download trend
Daily snapshots, last 90 days (28 Jul – 25 Oct)
3.2 M139 K
Qwen3-30B-A3B
Meta-Llama-3-8B
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Meta-Llama-3-8B · fp16
19.4 GB / 24 GB
Qwen3-30B-A3B · fp16
72.3 GB / 24 GB