Llama 3.1 8B Instruct
Meta's workhorse — the base most add-ons target
Install with Bobbin
Don't have the app? Download it here.
The most widely fine-tuned open model of its generation. If you plan to buy adapters later, compatibility is best here.
Older than the other 8GB options, so expect weaker reasoning than Qwen3 8B — it is here for the ecosystem, not the raw ability.
Available versions
| Quantization | Size | VRAM | RAM | Context | |
|---|---|---|---|---|---|
| Q4_K_M | 4.9 GB | 6.1 GB | 9.8 GB | 8k | Install |
Memory needed grows with the length of a conversation, so these figures are for the context shown. Anything marked est. is worked out from the file size rather than measured on real hardware — the app says so there too. The desktop app checks all of it against your actual machine before installing.