| model | architecture | parameters | context length |
embedding length |
quantization | temperature | capabilities | system prompt | (raw) | (index) |
|---|---|---|---|---|---|---|---|---|---|---|
| bakllava:7b | llama | 7.2B | 32768 | 4096 | Q4_0 | completion vision |
raw | index | ||
| codellama:7b | llama | 6.7B | 16384 | 4096 | Q4_0 | completion |
raw | index | ||
| deepcoder:1.5b | qwen2 | 1.8B | 131072 | 1536 | Q4_K_M | 0.6 | completion |
raw | index | |
| deepseek-r1:1.5b | qwen2 | 1.8B | 131072 | 1536 | Q4_K_M | completion thinking |
raw | index | ||
| deepseek-r1:8b | qwen3 | 8.2B | 131072 | 4096 | Q4_K_M | 0.6 | completion thinking |
raw | index | |
| dolphin3:8b | llama | 8.0B | 131072 | 4096 | Q4_K_M | completion |
You are Dolphin, a helpful AI assistant. | raw | index | |
| gemma3:1b | gemma3 | 999.89M | 32768 | 1152 | Q4_K_M | 1 | completion |
raw | index | |
| gemma3:4b | gemma3 | 4.3B | 131072 | 2560 | Q4_K_M | 1 | completion vision |
raw | index | |
| gemma:2b | gemma | 2.5B | 8192 | 2048 | Q4_0 | completion |
raw | index | ||
| granite3.2-vision:2b | granite | 2.5B | 16384 | 2048 | Q4_K_M | 0 | completion tools vision |
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. | raw | index |
| granite3.3:2b | granite | 2.5B | 131072 | 2048 | Q4_K_M | completion tools |
raw | index | ||
| llava-llama3:8b | llama | 8.0B | 8192 | 4096 | Q4_K_M | completion vision |
raw | index | ||
| llava-phi3:3.8b | llama | 3.8B | 4096 | 3072 | Q4_K_M | completion vision |
raw | index | ||
| llava:7b | llama | 7.2B | 32768 | 4096 | Q4_0 | completion vision |
raw | index | ||
| minicpm-v:8b | qwen2 | 7.6B | 32768 | 3584 | Q4_0 | completion vision |
raw | index | ||
| mistral:7b | llama | 7.2B | 32768 | 4096 | Q4_0 | completion tools |
raw | index | ||
| moondream:1.8b | phi2 | 1.4B | 2048 | 2048 | Q4_0 | 0 | completion vision |
raw | index | |
| qwen2.5-coder:7b | qwen2 | 7.6B | 32768 | 3584 | Q4_K_M | completion tools insert |
You are Qwen, created by Alibaba Cloud. You are a helpful assistant. | raw | index | |
| qwen2.5vl:3b | qwen25vl | 3.8B | 128000 | 2048 | Q4_K_M | 0.0001 | completion vision |
You are a helpful assistant. | raw | index |
| qwen2.5vl:7b | qwen25vl | 8.3B | 128000 | 3584 | Q4_K_M | 0.0001 | completion vision |
You are a helpful assistant. | raw | index |
| qwen3:1.7b | qwen3 | 2.0B | 40960 | 2048 | Q4_K_M | 0.6 | completion tools thinking |
raw | index | |
| stable-code:3b | stablelm | 2.8B | 16384 | 2560 | Q4_0 | completion |
raw | index | ||
| starcoder:7b | starcoder | 7.5B | 8192 | 4096 | Q4_0 | completion |
raw | index |