Qwen3-8B vs LFM2.5-24B-A2B
Specs, VRAM requirements and download trends — updated 25 October 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-8B | LFM2.5-24B-A2B |
|---|---|---|
| Deployment | Open weights | Open weights · also via API |
| Parameters | 8.2 B | 24.0 B |
| Architecture | Qwen3ForCausalLM | Lfm2MoeForCausalLM |
| Context length | 40,960 | 131,072 |
| Licence | apache-2.0 | other |
| Commercial use | Allowed | Unknown |
| Languages | — | 16 |
| Downloads 30d | 8,164,793 | 18,100 |
| Downloads all time | 133.8 M | 18 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-04-27 | 2026-10-12 |
| API input price / 1M tokens | not on OpenRouter | $0.05 |
| API output price / 1M tokens | not on OpenRouter | $0.70 |
| Est. cost per 1M input + 1M output tokens | not on OpenRouter | $0.75 |
| Cached input / 1M tokens | not on OpenRouter | $0.025 |
| AA Intelligence Index | not on OpenRouter | — |
| AA Coding Index | not on OpenRouter | — |
| AA Agentic Index | not on OpenRouter | — |
| Max output tokens | not on OpenRouter | 8,192 |
| API providers | not on OpenRouter | 1 |
| Tool calling | not on OpenRouter | Yes |
| Reasoning mode | not on OpenRouter | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
LFM2.5-24B-A2B
$0.75
Download trend
Daily snapshots, last 90 days (28 Jul – 25 Oct)
16.6 M13 K
Qwen3-8B
LFM2.5-24B-A2B
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-8B · fp16
19.7 GB / 24 GB
LFM2.5-24B-A2B · fp16 @ 128K ctx
110.8 GB / 24 GB