A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function calling.
ollama run nemotron-mini
Ollama kurulu değil mi? ollama.com/download — Windows, macOS ve Linux için ücretsiz. İlk çalıştırmada model indirilir, sonrası tamamen çevrimdışıdır.
Boyut büyüdükçe kalite artar, donanım ihtiyacı yükselir. Başlangıç için küçük varyantı deneyin.
| Etiket | Boyut | Bağlam | Girdi | Komut |
|---|---|---|---|---|
| latest | 2.7GB | 4K | Text |
ollama run nemotron-mini:latest
|
| 4b | 2.7GB | 4K | Text |
ollama run nemotron-mini:4b
|
| 4b-instruct-q2_K | 1.9GB | 4K | Text |
ollama run nemotron-mini:4b-instruct-q2_K
|
| 4b-instruct-q3_K_S | 2.1GB | 4K | Text |
ollama run nemotron-mini:4b-instruct-q3_K_S
|
| 4b-instruct-q3_K_M | 2.3GB | 4K | Text |
ollama run nemotron-mini:4b-instruct-q3_K_M
|
| 4b-instruct-q3_K_L | 2.5GB | 4K | Text |
ollama run nemotron-mini:4b-instruct-q3_K_L
|
| 4b-instruct-q4_0 | 2.6GB | 4K | Text |
ollama run nemotron-mini:4b-instruct-q4_0
|
| 4b-instruct-q4_1 | 2.8GB | 4K | Text |
ollama run nemotron-mini:4b-instruct-q4_1
|
| 4b-instruct-q4_K_S | 2.6GB | 4K | Text |
ollama run nemotron-mini:4b-instruct-q4_K_S
|
| 4b-instruct-q4_K_M | 2.7GB | 4K | Text |
ollama run nemotron-mini:4b-instruct-q4_K_M
|
| 4b-instruct-q5_0 | 3.0GB | 4K | Text |
ollama run nemotron-mini:4b-instruct-q5_0
|
| 4b-instruct-q5_1 | 3.2GB | 4K | Text |
ollama run nemotron-mini:4b-instruct-q5_1
|
| 4b-instruct-q5_K_S | 3.0GB | 4K | Text |
ollama run nemotron-mini:4b-instruct-q5_K_S
|
| 4b-instruct-q5_K_M | 3.1GB | 4K | Text |
ollama run nemotron-mini:4b-instruct-q5_K_M
|
| 4b-instruct-q6_K | 3.4GB | 4K | Text |
ollama run nemotron-mini:4b-instruct-q6_K
|
| 4b-instruct-q8_0 | 4.5GB | 4K | Text |
ollama run nemotron-mini:4b-instruct-q8_0
|
| 4b-instruct-fp16 | 8.4GB | 4K | Text |
ollama run nemotron-mini:4b-instruct-fp16
|
Nemotron-Mini-4B-Instruct is a model for generating responses for roleplaying, retrieval augmented generation, and function calling. It is a small language model (SLM) optimized through distillation, pruning and quantization for speed and on-device deployment.
This instruct model is optimized for roleplay, RAG QA, and function calling in English. It supports a context length of 4,096 tokens. This model is ready for commercial use.