Qwen2.5-0.5B-Instruct vs LFM3-1.7B
Specs, VRAM requirements and download trends — updated 10 November 2026.
Qwen · A · Open weights
Params
490 M
Context
32,768
30d
4.5 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-0.5B-Instruct | LFM3-1.7B |
|---|---|---|
| Deployment | Open weights | Open weights · also via API |
| Parameters | 490 M | 1.7 B |
| Architecture | Qwen2ForCausalLM | Lfm3ForCausalLM |
| Context length | 32,768 | 262,144 |
| Licence | apache-2.0 | other |
| Commercial use | Allowed | Unknown |
| Languages | 1 | 16 |
| Downloads 30d | 4,524,207 | 78,750 |
| Downloads all time | 78.1 M | 79 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-09-16 | 2026-10-23 |
| API input price / 1M tokens | not on OpenRouter | $0.08 |
| API output price / 1M tokens | not on OpenRouter | $0.20 |
| Est. cost per 1M input + 1M output tokens | not on OpenRouter | $0.28 |
| Cached input / 1M tokens | not on OpenRouter | $0.02 |
| 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
LFM3-1.7B
$0.28
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
8.7 M66 K
Qwen2.5-0.5B-Instruct
LFM3-1.7B
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-0.5B-Instruct · fp16
1.7 GB / 24 GB
LFM3-1.7B · fp16 @ 256K ctx
12.6 GB / 24 GB