LFM2.5-230M
LFM2.5 · LFM2.5-230M
Open weights
- Context
- Not documented
- Max. output
- Not documented
- Knowledge cutoff
- Not documented
AI models
LFM2.5-230M-Base
LFM2.5 · LFM2.5-230M-Base
Open weights
- Context
- Not documented
- Max. output
- Not documented
- Knowledge cutoff
- Not documented
LFM2.5-24B-A2B
LFM2.5 · LFM2.5-24B-A2B
Open weights
- Context
- Not documented
- Max. output
- Not documented
- Knowledge cutoff
- Not documented
LFM2.5-24B-A2B-Base
LFM2.5 · LFM2.5-24B-A2B-Base
Open weights
- Context
- Not documented
- Max. output
- Not documented
- Knowledge cutoff
- Not documented
LFM2.5-350M
LFM2.5 · LFM2.5-350M
Open weights
- Context
- Not documented
- Max. output
- Not documented
- Knowledge cutoff
- Not documented
LFM2.5-350M-Base
LFM2.5 · LFM2.5-350M-Base
Open weights
- Context
- Not documented
- Max. output
- Not documented
- Knowledge cutoff
- Not documented
LFM2.5-8B-A1B
LFM2.5 · LFM2.5-8B-A1B
Open weights
- Context
- Not documented
- Max. output
- Not documented
- Knowledge cutoff
- Not documented
LFM2.5-8B-A1B-Base
LFM2.5 · LFM2.5-8B-A1B-Base
Open weights
- Context
- Not documented
- Max. output
- Not documented
- Knowledge cutoff
- Not documented
LFM2.5-VL-1.6B
LFM2.5 · LFM2.5-VL-1.6B
Open weights
- Context
- Not documented
- Max. output
- Not documented
- Knowledge cutoff
- Not documented
LFM2.5-VL-1.6B-Extract
LFM2.5 · LFM2.5-VL-1.6B-Extract
Open weights
- Context
- Not documented
- Max. output
- Not documented
- Knowledge cutoff
- Not documented
LFM2.5-VL-3B
LFM2.5 · LFM2.5-VL-3B
Open weights
- Context
- Not documented
- Max. output
- Not documented
- Knowledge cutoff
- Not documented
LFM2.5-VL-450M
LFM2.5 · LFM2.5-VL-450M
Open weights
- Context
- Not documented
- Max. output
- Not documented
- Knowledge cutoff
- Not documented
LFM2.5-VL-450M-Extract
LFM2.5 · LFM2.5-VL-450M-Extract
Open weights
- Context
- Not documented
- Max. output
- Not documented
- Knowledge cutoff
- Not documented
Llama 2 13b
Llama 2 · meta-llama/Llama-2-13b
Open weights
- Context
- 4,000 tokens
- Max. output
- Not documented
- Knowledge cutoff
- Not documented
Llama 2 13b chat
Llama 2 · meta-llama/Llama-2-13b-chat
Open weights
- Context
- 4,000 tokens
- Max. output
- Not documented
- Knowledge cutoff
- Not documented
Llama 2 70b
Llama 2 · meta-llama/Llama-2-70b
Open weights
- Context
- 4,000 tokens
- Max. output
- Not documented
- Knowledge cutoff
- Not documented
Llama 2 70b chat
Llama 2 · meta-llama/Llama-2-70b-chat
Open weights
- Context
- 4,000 tokens
- Max. output
- Not documented
- Knowledge cutoff
- Not documented
Llama 2 7b
Llama 2 · meta-llama/Llama-2-7b
Open weights
- Context
- 4,000 tokens
- Max. output
- Not documented
- Knowledge cutoff
- Not documented
Llama 2 7b chat
Llama 2 · meta-llama/Llama-2-7b-chat
Open weights
- Context
- 4,000 tokens
- Max. output
- Not documented
- Knowledge cutoff
- Not documented
Llama 3.2 1B
Llama 3.2 · meta-llama/Llama-3.2-1B
Open weights
- Context
- 128,000 tokens
- Max. output
- Not documented
- Knowledge cutoff
- Dec 2023Knowledge cutoff · month precision
Llama 3.2 1B Instruct
Llama 3.2 · meta-llama/Llama-3.2-1B-Instruct
Open weights
- Context
- 128,000 tokens
- Max. output
- Not documented
- Knowledge cutoff
- Dec 2023Knowledge cutoff · month precision
Llama 3.2 3B
Llama 3.2 · meta-llama/Llama-3.2-3B
Open weights
- Context
- 128,000 tokens
- Max. output
- Not documented
- Knowledge cutoff
- Dec 2023Knowledge cutoff · month precision
Llama 3.2 3B Instruct
Llama 3.2 · meta-llama/Llama-3.2-3B-Instruct
Open weights
- Context
- 128,000 tokens
- Max. output
- Not documented
- Knowledge cutoff
- Dec 2023Knowledge cutoff · month precision
Llama 3.3 70B Instruct
Llama 3.3 · meta-llama/Llama-3.3-70B-Instruct
Open weights
- Context
- 128,000 tokens
- Max. output
- Not documented
- Knowledge cutoff
- Dec 2023Knowledge cutoff · month precision
Go beyond the spec sheet
The decisions behind the numbers.
Source-checked guides to pricing, usable context, and access restrictions.