SmolLM2-135M vs LFM2.5-350M-GGUF
Specs, VRAM requirements and download trends — updated 10 November 2026.
HuggingFaceTB · A · Open weights
Params
130 M
Context
8,192
30d
2.5 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | SmolLM2-135M | LFM2.5-350M-GGUF |
|---|---|---|
| Parameters | 130 M | 350 M |
| Architecture | LlamaForCausalLM | — |
| Context length | 8,192 | 128,000 |
| Licence | apache-2.0 | other |
| Commercial use | Allowed | Unknown |
| Languages | 1 | 8 |
| Downloads 30d | 2,526,884 | 164,626 |
| Downloads all time | 24.3 M | 455 K |
| Quantizations on the Hub | SAFETENSORS | GGUF, SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-10-31 | 2026-03-25 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
2.6 M142 K
SmolLM2-135M
LFM2.5-350M-GGUF
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
SmolLM2-135M · fp16
0.8 GB / 24 GB
LFM2.5-350M-GGUF · Q4_0
0.8 GB / 24 GB
LFM2.5-350M-GGUF · fp16 @ 125K ctx
2.9 GB / 24 GB