Qwen/Qwen2.5-Math-72B GGUF Quantizations π
Optimized GGUF quantization files for enhanced model performance
Powered by Featherless AI - run any model you'd like for a simple small fee.
Available Quantizations π
Quantization Type | File | Size |
---|---|---|
IQ4_XS | Qwen-Qwen2.5-Math-72B-IQ4_XS | 38302.65 MB (folder) |
Q2_K | Qwen-Qwen2.5-Math-72B-Q2_K | 28430.71 MB (folder) |
Q3_K_L | Qwen-Qwen2.5-Math-72B-Q3_K_L | 37675.12 MB (folder) |
Q3_K_M | Qwen-Qwen2.5-Math-72B-Q3_K_M | 35952.31 MB (folder) |
Q3_K_S | Qwen-Qwen2.5-Math-72B-Q3_K_S | 32890.12 MB (folder) |
Q4_K_M | Qwen-Qwen2.5-Math-72B-Q4_K_M | 45219.15 MB (folder) |
Q4_K_S | Qwen-Qwen2.5-Math-72B-Q4_K_S | 41856.03 MB (folder) |
Q5_K_M | Qwen-Qwen2.5-Math-72B-Q5_K_M | 51925.15 MB (folder) |
Q5_K_S | Qwen-Qwen2.5-Math-72B-Q5_K_S | 48995.15 MB (folder) |
Q6_K | Qwen-Qwen2.5-Math-72B-Q6_K | 61366.68 MB (folder) |
Q8_0 | Qwen-Qwen2.5-Math-72B-Q8_0 | 73683.37 MB (folder) |
β‘ Powered by Featherless AI
Key Features
- π₯ Instant Hosting - Deploy any Llama model on HuggingFace instantly
- π οΈ Zero Infrastructure - No server setup or maintenance required
- π Vast Compatibility - Support for 2400+ models and counting
- π Affordable Pricing - Starting at just $10/month
Links:
Get Started | Documentation | Models
- Downloads last month
- 61