daga meta-llama
Llama 3.2 1B Instruct
meta-llama/Llama-3.2-1B-Instruct
Duk lambobin ƙiyasi ne. Ainihin amfani da ma’adanar ajiya da gudu sun dogara ne da direbobinku, saitunanku da sauran shirye-shiryen da ke gudana.
- Ma’auni (parameters)
- 1.2B
- Lasisi
- llama3.2
- An wallafa
- Sep 18, 2024
Lasisin na mai samar da samfurin ne. Ku duba sharuɗɗansa kafin ku yi amfani da samfurin.
Hugging Face na neman ku amince da sharuɗɗan mai samarwa kafin ku sauke wannan samfurin. Ba a sayar da kit don shi.
Na asali a Hugging Face ↗Ma’adanar da ake buƙata bisa quantization
A tokens 8,192 na mahalli, har da 0.8 GB na muhallin gudanarwa.
| Quantization | Fayil ɗin samfuri | Jimla |
|---|---|---|
| Q4_K_M | 0.7 GB | 1.6 GB(ƙiyasi) |
| Q5_K_M | 0.9 GB | 1.8 GB(ƙiyasi) |
| Q6_K | 1.0 GB | 1.9 GB(ƙiyasi) |
| Q8_0 | 1.3 GB | 2.2 GB(ƙiyasi) |
| F16 | 2.5 GB | 3.5 GB(ƙiyasi) |
Na’urorin da ke gudanar da shi a kan katin zane
A Q4_K_M da tokens 8,192 na mahalli.
- 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
Samfuri ɗaya ta hanyar API
Mai sayarwa mafi arha: Inference, $0.09 a wata a amfani na asali (buƙatu 200 a rana).
Duba farashi a Model Price MapBayanan samfura sun fito ne daga jerin jama’a na Hugging Face (sunaye, girma, lasisi). Kowane shafin samfuri yana da hanyar haɗi zuwa na asali.