Llama-3.2-1B-Instruct-FP8-dynamic vs LFM2.5-1.2B-Instruct
Specs, VRAM requirements and download trends — updated 11 August 2026.
RedHatAI · A · Open weights
Params
1.5 B
Context
131,072
30d
170 K
llama3.2 licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Llama-3.2-1B-Instruct-FP8-dynamic | LFM2.5-1.2B-Instruct |
|---|---|---|
| Parameters | 1.5 B | 1.2 B |
| Architecture | LlamaForCausalLM | Lfm2ForCausalLM |
| Context length | 131,072 | 128,000 |
| Licence | llama3.2 | other |
| Commercial use | Conditional | Unknown |
| Languages | 8 | 8 |
| Downloads 30d | 170,223 | 201,456 |
| Downloads all time | 13.9 M | 2.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-09-25 | 2026-01-06 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
1.1 M170 K
Llama-3.2-1B-Instruct-FP8-dynamic
LFM2.5-1.2B-Instruct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
LFM2.5-1.2B-Instruct · fp16 @ 125K ctx
5.8 GB / 24 GB
Llama-3.2-1B-Instruct-FP8-dynamic · fp16 @ 128K ctx
6.3 GB / 24 GB