Qwen2.5-3B-Instruct vs LFM2.5-2.6B
Specs, VRAM requirements and download trends — updated 4 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-3B-Instruct | LFM2.5-2.6B |
|---|---|---|
| Deployment | Open weights | Open weights · also via API |
| Parameters | 3.1 B | 2.7 B |
| Architecture | Qwen2ForCausalLM | Lfm2ForCausalLM |
| Context length | 32,768 | 131,072 |
| Licence | other | other |
| Commercial use | Unknown | Unknown |
| Languages | 1 | 16 |
| Downloads 30d | 2,587,484 | 187,515 |
| Downloads all time | 125.6 M | 204 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-09-17 | 2026-07-28 |
| API input price / 1M tokens | not on OpenRouter | $0.35 |
| API output price / 1M tokens | not on OpenRouter | $0.50 |
| Est. cost per 1M input + 1M output tokens | not on OpenRouter | $0.85 |
| Cached input / 1M tokens | not on OpenRouter | $0.04 |
| AA Intelligence Index | not on OpenRouter | — |
| AA Coding Index | not on OpenRouter | 7.7 |
| 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
LFM2.5-2.6B
$0.85
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
7.6 M183 K
Qwen2.5-3B-Instruct
LFM2.5-2.6B
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-3B-Instruct · fp16
7.8 GB / 24 GB
LFM2.5-2.6B · fp16 @ 128K ctx
12.9 GB / 24 GB