Qwen2 Math features 3 model sizes (1.5B, 7B, and 72B) each with a base model, for completion, few-shot inference, and fine-tuning, and an instruct model for chatting.
qwen2-math
Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of open-source models and even closed-source models (e.g., GPT4o).
1.5b
7b
72b
Hızlı Kurulum (Ollama kuruluysa)
ollama run qwen2-math
Ollama kurulu değil mi? ollama.com/download — Windows, macOS ve Linux için ücretsiz. İlk çalıştırmada model indirilir, sonrası tamamen çevrimdışıdır.
Varyantlar
Boyut büyüdükçe kalite artar, donanım ihtiyacı yükselir. Başlangıç için küçük varyantı deneyin.
| Etiket | Boyut | Bağlam | Girdi | Komut |
|---|---|---|---|---|
| latest | 4.4GB | 4K | Text |
ollama run qwen2-math:latest
|
| 1.5b | 935MB | 4K | Text |
ollama run qwen2-math:1.5b
|
| 7b | 4.4GB | 4K | Text |
ollama run qwen2-math:7b
|
| 72b | 41GB | 4K | Text |
ollama run qwen2-math:72b
|
| 1.5b-instruct | 935MB | 4K | Text |
ollama run qwen2-math:1.5b-instruct
|
| 1.5b-instruct-q2_K | 676MB | 4K | Text |
ollama run qwen2-math:1.5b-instruct-q2_K
|
| 1.5b-instruct-q3_K_S | 761MB | 4K | Text |
ollama run qwen2-math:1.5b-instruct-q3_K_S
|
| 1.5b-instruct-q3_K_M | 824MB | 4K | Text |
ollama run qwen2-math:1.5b-instruct-q3_K_M
|
| 1.5b-instruct-q3_K_L | 880MB | 4K | Text |
ollama run qwen2-math:1.5b-instruct-q3_K_L
|
| 1.5b-instruct-q4_0 | 935MB | 4K | Text |
ollama run qwen2-math:1.5b-instruct-q4_0
|
| 1.5b-instruct-q4_1 | 1.0GB | 4K | Text |
ollama run qwen2-math:1.5b-instruct-q4_1
|
| 1.5b-instruct-q4_K_S | 940MB | 4K | Text |
ollama run qwen2-math:1.5b-instruct-q4_K_S
|
| 1.5b-instruct-q4_K_M | 986MB | 4K | Text |
ollama run qwen2-math:1.5b-instruct-q4_K_M
|
| 1.5b-instruct-q5_0 | 1.1GB | 4K | Text |
ollama run qwen2-math:1.5b-instruct-q5_0
|
| 1.5b-instruct-q5_1 | 1.2GB | 4K | Text |
ollama run qwen2-math:1.5b-instruct-q5_1
|
| 1.5b-instruct-q5_K_S | 1.1GB | 4K | Text |
ollama run qwen2-math:1.5b-instruct-q5_K_S
|
| 1.5b-instruct-q5_K_M | 1.1GB | 4K | Text |
ollama run qwen2-math:1.5b-instruct-q5_K_M
|
| 1.5b-instruct-q6_K | 1.3GB | 4K | Text |
ollama run qwen2-math:1.5b-instruct-q6_K
|
| 1.5b-instruct-q8_0 | 1.6GB | 4K | Text |
ollama run qwen2-math:1.5b-instruct-q8_0
|
| 1.5b-instruct-fp16 | 3.1GB | 4K | Text |
ollama run qwen2-math:1.5b-instruct-fp16
|
| 7b-instruct | 4.4GB | 4K | Text |
ollama run qwen2-math:7b-instruct
|
| 7b-instruct-q2_K | 3.0GB | 4K | Text |
ollama run qwen2-math:7b-instruct-q2_K
|
| 7b-instruct-q3_K_S | 3.5GB | 4K | Text |
ollama run qwen2-math:7b-instruct-q3_K_S
|
| 7b-instruct-q3_K_M | 3.8GB | 4K | Text |
ollama run qwen2-math:7b-instruct-q3_K_M
|
| 7b-instruct-q3_K_L | 4.1GB | 4K | Text |
ollama run qwen2-math:7b-instruct-q3_K_L
|
27 varyant daha var — tümü için ollama.com.