Qwen3-0.6B-FP8 vs LFM2.5-1.2B-Instruct
Specs, VRAM requirements and download trends — updated 30 July 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-0.6B-FP8 | LFM2.5-1.2B-Instruct |
|---|---|---|
| Parameters | 750 M | 1.2 B |
| Architecture | Qwen3ForCausalLM | Lfm2ForCausalLM |
| Context length | 40,960 | 128,000 |
| Licence | apache-2.0 | other |
| Commercial use | Allowed | Unknown |
| Languages | — | 8 |
| Downloads 30d | 269,828 | 201,456 |
| Downloads all time | 13.3 M | 2.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-04-28 | 2026-01-06 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
1.7 M201 K
Qwen3-0.6B-FP8
LFM2.5-1.2B-Instruct
A overtook B on 14 Sep
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-0.6B-FP8 · fp16
1.8 GB / 24 GB
LFM2.5-1.2B-Instruct · fp16 @ 125K ctx
5.8 GB / 24 GB