- 3 % discount on prepayment
- Insured shipping from Switzerland
- Sustainable: refurbished instead of new
- Warranty on all cards
- 3 % discount on prepayment
- Insured shipping from Switzerland
- Sustainable: refurbished instead of new
- Warranty on all cards
← Back to overview
LFM2.5-8B-A1B
Liquid AI
GermanLfm1.0
Open language model for chat and text. 2 sizes from 2.7B to 8.5B parameters, partly mixture-of-experts (only a part of the parameters is active per token).
- Mixture-of-experts: 8.5B parameters in total, of which 1.0B active per token. Memory requirement depends on all parameters, speed on the active ones.
Settings
Quality
4 bit (Q4_K_M) is the most common choice: good quality with low memory requirements.
Context length: 8k tokens
4k64k
How much text the model keeps in view at once. More context needs more memory.
Recommendation
1× H100 80 GB
The model needs about 6.7 GB of memory. Hopper, FP8 support.
- Weights
- 5.1 GB
- KV cache
- 0.1 GB
- Speed
- ~1'573.0 Tok./s
More suitable configurations
| Card | Quantity | Tok./s | Status |
|---|---|---|---|
| Tesla T4 16 GB | 1× | 272.2 | 2-3 weeks delivery time |
| Tesla P100 16 GB | 1× | 342.9 | 2-3 weeks delivery time |
| Tesla P40 24 GB | 1× | 321.4 | 2-3 weeks delivery time |
| Tesla V100 16 GB | 1× | 758.1 | in stock |
| Tesla V100 32 GB | 1× | 758.1 | On order, delivery time approx. 1 week |
| AMD Instinct MI50 16 GB | 1× | 581.2 | in stock |
| AMD Instinct MI50 32 GB | 1× | 581.2 | in stock |
| AMD Instinct MI60 32 GB | 1× | 536.6 | 2-3 weeks delivery time |
| AMD Instinct MI100 32 GB | 1× | 648.9 | 2-3 weeks delivery time |
| A30 24 GB | 1× | 733.5 | 2-3 weeks delivery time |
| RTX A5000 24 GB | 1× | 764.2 | 2-3 weeks delivery time |
| A40 48 GB | 1× | 728.9 | 2-3 weeks delivery time |
