LFM2.5-2.6B-GGUF vs SmolLM3-3B-Base
Specs, VRAM requirements and download trends — updated 23 September 2026.
HuggingFaceTB · B · Open weights
Params
3.1 B
Context
65,536
30d
213 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | LFM2.5-2.6B-GGUF | SmolLM3-3B-Base |
|---|---|---|
| Parameters | 2.6 B | 3.1 B |
| Architecture | — | SmolLM3ForCausalLM |
| Context length | 131,072 | 65,536 |
| Licence | other | apache-2.0 |
| Commercial use | Unknown | Allowed |
| Languages | 16 | 8 |
| Downloads 30d | 186,819 | 213,155 |
| Downloads all time | 2.5 M | 2.0 M |
| Quantizations on the Hub | GGUF, SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-08-01 | 2025-06-19 |
Download trend
Daily snapshots, last 89 days (14 Aug – 10 Nov)
1.2 M161 K
LFM2.5-2.6B-GGUF
SmolLM3-3B-Base
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
LFM2.5-2.6B-GGUF · Q4_0
2.6 GB / 24 GB
SmolLM3-3B-Base · fp16
7.7 GB / 24 GB
LFM2.5-2.6B-GGUF · fp16 @ 128K ctx
18.6 GB / 24 GB