- Context window
- 131,072 tokens
- Total parameters
- 8.03 B
- Open weights
- Yes
- Model license
- other
GeekRadar / The comparison desk
COMPARE.
AI- Context window
- 16,384 tokens
- Open weights
- Yes
- Model license
- other
- Checkpoint tensor payload
- 16.25 GiB
Llama-3.1-Tulu-3-405B
Models- Context window
- 131,072 tokens
- Total parameters
- 405.85 B
- Open weights
- Yes
- Model license
- llama3.1
Llama-3.1-Tulu-3-70B
Models- Context window
- 131,072 tokens
- Total parameters
- 70.55 B
- Open weights
- Yes
- Model license
- llama3.1
Llama-3.1-Tulu-3-70B-DPO
Models- Context window
- 131,072 tokens
- Total parameters
- 70.55 B
- Open weights
- Yes
- Model license
- llama3.1
Llama-3.1-Tulu-3-8B
Models- Context window
- 131,072 tokens
- Total parameters
- 8.03 B
- Open weights
- Yes
- Model license
- llama3.1
Llama-3.1-Tulu-3-8B-DPO
Models- Context window
- 131,072 tokens
- Total parameters
- 8.03 B
- Open weights
- Yes
- Model license
- llama3.1
Llama-3.1-Tulu-3-8B-SFT
Models- Context window
- 131,072 tokens
- Total parameters
- 8.03 B
- Open weights
- Yes
- Model license
- llama3.1
Llama-3.1-Tulu-3.1-8B
Models- Context window
- 131,072 tokens
- Total parameters
- 8.03 B
- Open weights
- Yes
- Model license
- llama3.1
Llama-3.2-1B
Models- Context window
- 131,072 tokens
- Total parameters
- 1.24 B
- Open weights
- Yes
- Model license
- llama3.2
Llama3-ChatQA-1.5-8B
Models- Context window
- 8,192 tokens
- Total parameters
- 8.03 B
- Open weights
- Yes
- Model license
- llama3
llamagate/codellama-7b
Models*- Maximum output
- 4,096 tokens*
- Maximum input
- 16,384 tokens*
- Tool calling
- Yes*
- Structured output
- Yes*
- Maximum output
- 4,096 tokens*
- Maximum input
- 16,384 tokens*
- Tool calling
- Yes*
- Structured output
- Yes*
llamagate/dolphin3-8b
Models*- Maximum output
- 8,192 tokens*
- Maximum input
- 128,000 tokens*
- Tool calling
- Yes*
- Structured output
- Yes*
llamagate/llama-3.1-8b
Models*- Maximum output
- 8,192 tokens*
- Maximum input
- 131,072 tokens*
- Tool calling
- Yes*
- Structured output
- Yes*
llamagate/llama-3.2-3b
Models*- Maximum output
- 8,192 tokens*
- Maximum input
- 131,072 tokens*
- Tool calling
- Yes*
- Structured output
- Yes*
llamagate/llava-7b
Models*- Maximum output
- 2,048 tokens*
- Maximum input
- 4,096 tokens*
- Structured output
- Yes*
- API mode
- Chat*
llamagate/mistral-7b-v0.3
Models*- Maximum output
- 8,192 tokens*
- Maximum input
- 32,768 tokens*
- Tool calling
- Yes*
- Structured output
- Yes*
llamagate/qwen2.5-coder-7b
Models*- Maximum output
- 8,192 tokens*
- Maximum input
- 32,768 tokens*
- Tool calling
- Yes*
- Structured output
- Yes*
llamagate/qwen3-8b
Models*- Maximum output
- 8,192 tokens*
- Maximum input
- 32,768 tokens*
- Tool calling
- Yes*
- Structured output
- Yes*
LongWriter-llama3.1-8b
Models- Context window
- 131,072 tokens
- Total parameters
- 8.03 B
- Open weights
- Yes
- Model license
- llama3.1
MagenticBrain
Models- Context window
- 40,960 tokens
- Total parameters
- 14.77 B
- Open weights
- Yes
- Model license
- mit
MediPhi
Models- Context window
- 131,072 tokens
- Total parameters
- 3.82 B
- Open weights
- Yes
- Model license
- mit
MediPhi-Clinical
Models- Context window
- 131,072 tokens
- Total parameters
- 3.82 B
- Open weights
- Yes
- Model license
- mit
0 selected Compare 0
* Provisional data