saka meta-llama
Llama 3.2 1B Instruct
meta-llama/Llama-3.2-1B-Instruct
Kabeh angka iku mung prakiraan. Panggunaan memori lan kacepetan sing sabenere gumantung marang driver, setelan, lan program liyane sing lagi mlaku.
- Parameter
- 1.2B
- Lisensi
- llama3.2
- Diterbitake
- Sep 18, 2024
Lisensi iki duweke pembuat model. Priksanana ketentuane sadurunge Panjenengan nggunakake model iki.
Hugging Face njaluk Panjenengan nampa ketentuan pembuat sadurunge ngundhuh model iki. Kanggo model iki ora ana kit sing didol.
Asline ing Hugging Face ↗Memori sing dibutuhake miturut kuantisasi
Ing konteks 8,192 token, kalebu 0,8 GB kanggo runtime.
| Kuantisasi | Berkas model | Total |
|---|---|---|
| Q4_K_M | 0.7 GB | 1.6 GB(kira-kira) |
| Q5_K_M | 0.9 GB | 1.8 GB(kira-kira) |
| Q6_K | 1.0 GB | 1.9 GB(kira-kira) |
| Q8_0 | 1.3 GB | 2.2 GB(kira-kira) |
| F16 | 2.5 GB | 3.5 GB(kira-kira) |
Hardware sing mlakokake model iki ing kertu grafis
Ing Q4_K_M lan konteks 8,192 token.
- 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
Model sing padha liwat API
Penjual paling murah: Inference, $0.09 sasasi kanthi panggunaan baku (200 panjaluk saben dina).
Deleng rega ing Model Price MapRincian model asale saka dhaptar umum Hugging Face (jeneng, ukuran, lisensi). Saben kaca model nyambung menyang asline.