nke meta-llama
Llama 3.2 1B Instruct
meta-llama/Llama-3.2-1B-Instruct
Ọnụọgụgụ niile bụ atụmatụ. Ojiji ebe nchekwa n'ezie na ọsọ na-adabere na draịva gị, ntọala gị na mmemme ndị ọzọ na-agba.
- Paramita
- 1.2B
- Ikikere
- llama3.2
- E bipụtara
- Sep 18, 2024
Ikikere ahụ bụ nke onye mepụtara ụdị ahụ. Lelee ọnọdụ ya tupu ị jiri ụdị ahụ.
Hugging Face chọrọ ka ị nabata ọnọdụ onye mepụtara ya tupu ị budata ụdị a. A naghị ere kit maka ya.
Nke mbụ na Hugging Face ↗Ebe nchekwa achọrọ site na quantization
Na token 8,192 nke ọnọdụ okwu, gụnyere 0.8 GB maka gburugburu ịgba ọsọ.
| Quantization | Faịlụ ụdị | Ngụkọta |
|---|---|---|
| Q4_K_M | 0.7 GB | 1.6 GB(ihe dị ka) |
| Q5_K_M | 0.9 GB | 1.8 GB(ihe dị ka) |
| Q6_K | 1.0 GB | 1.9 GB(ihe dị ka) |
| Q8_0 | 1.3 GB | 2.2 GB(ihe dị ka) |
| F16 | 2.5 GB | 3.5 GB(ihe dị ka) |
Ngwa ngwa na-agba ya na kaadị eserese
Na Q4_K_M na token 8,192 nke ọnọdụ okwu.
- NVIDIA GeForce RTX 3060 (12 GB)
- NVIDIA GeForce RTX 3070
- NVIDIA GeForce RTX 3080 (10 GB)
- NVIDIA GeForce RTX 3090
- NVIDIA GeForce RTX 4070
- NVIDIA GeForce RTX 4070 Ti SUPER
- NVIDIA GeForce RTX 4080 SUPER
- NVIDIA GeForce RTX 4090
- NVIDIA GeForce RTX 5060 Ti (16 GB)
- NVIDIA GeForce RTX 5070
- NVIDIA GeForce RTX 5070 Ti
- NVIDIA GeForce RTX 5080
- NVIDIA GeForce RTX 5090
- AMD Radeon RX 7600
- AMD Radeon RX 7700 XT
- AMD Radeon RX 7800 XT
- AMD Radeon RX 7900 XT
- AMD Radeon RX 7900 XTX
- AMD Radeon RX 9070 XT
- Apple M1 Pro
- Apple M1 Max
- Apple M2
- Apple M2 Pro
- Apple M2 Max
- Apple M3
- Apple M3 Pro
- Apple M3 Max (30-core GPU)
- Apple M3 Max (40-core GPU)
- Apple M4
- Apple M4 Pro
- Apple M4 Max (32-core GPU)
- Apple M4 Max (40-core GPU)
- Apple M5
- AMD Ryzen AI Max+ 395
Otu ụdị ahụ site na API
Onye na-ere ya n'ọnụ ahịa kacha ala: Inference, $0.09 n'otu ọnwa n'ojiji ndabara (arịrịọ 200 n'ụbọchị).
Lee ọnụ ahịa ndị ahụ na Model Price MapNkọwa ụdị sitere n'ndepụta ọha nke Hugging Face (aha, nha, ikikere). Ibe ụdị ọ bụla nwere njikọ gaa na ihe mbụ.