Models / Llama
Can an RTX 3060 12GB run Llama 3.1 8B?
Dense 8B with a 128k context. Fits on small GPUs at Q4 and Q8.
- Stored parameters
- 8B
- Active parameters
- Dense
- Q4 total (estimate)
- 6.6 GB
- License
- Llama 3.1 Community License
Model card. Meta lists Llama 3.1 8B as an 8B model with a 128k context.
Compatibility
| Hardware | Q4 | Q8 | FP16 |
|---|---|---|---|
| M3 Pro 18GB Apple · 18 GB unified | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Tight estimate · KV at 8k No measured run | |
| M3 Ultra 512GB Apple · 512 GB unified | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| 2× NVIDIA GB10 NVIDIA · 256 GB unified | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| M3 Ultra 256GB Apple · 256 GB unified | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| M5 Ultra 256GB Apple · 256 GB unified | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| M2 Ultra 192GB Apple · 192 GB unified | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| NVIDIA GB10 NVIDIA · 128 GB unified | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| Ryzen AI Max+ 395 128GB AMD · 128 GB unified | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| M1 Ultra 128GB Apple · 128 GB unified | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| M5 Max 128GB Apple · 128 GB unified | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| 4× RTX 3090 NVIDIA · 96 GB VRAM | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| RTX Pro 6000 Blackwell NVIDIA · 96 GB VRAM | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| M5 Ultra 96GB Apple · 96 GB unified | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| Ryzen AI Max+ 395 64GB AMD · 64 GB unified | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| 2× RTX 3090 NVIDIA · 48 GB VRAM | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| M4 Pro 48GB Apple · 48 GB unified | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| M4 Max 36GB Apple · 36 GB unified | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| M5 Max 36GB Apple · 36 GB unified | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| RTX 5090 NVIDIA · 32 GB VRAM | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| Radeon AI Pro R9700 AMD · 32 GB VRAM | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | |
| Intel Arc Pro B70 Intel · 32 GB VRAM | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| M4 32GB Apple · 32 GB unified | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| M6 32GB Apple · 32 GB unified | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| RTX 3090 NVIDIA · 24 GB VRAM | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| RTX 4090 NVIDIA · 24 GB VRAM | 6.6 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run | |
| TITAN RTX NVIDIA · 24 GB VRAM | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| Radeon RX 7900 XTX AMD · 24 GB VRAM | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run |
| M4 Pro 24GB Apple · 24 GB unified | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Tight estimate · KV at 8k No measured run |
| RTX 4060 Ti 16GB NVIDIA · 16 GB VRAM | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Over estimate · KV at 8k No measured run |
| RTX 5060 Ti 16GB NVIDIA · 16 GB VRAM | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Over estimate · KV at 8k No measured run |
| RTX 5070 Ti NVIDIA · 16 GB VRAM | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Over estimate · KV at 8k No measured run |
| M4 16GB Apple · 16 GB unified | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Over estimate · KV at 8k No measured run |
| RTX 3060 12GB NVIDIA · 12 GB VRAM | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Over estimate · KV at 8k No measured run |
| RTX 3080 Ti NVIDIA · 12 GB VRAM | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Over estimate · KV at 8k No measured run |
| RTX 4070 Ti NVIDIA · 12 GB VRAM | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Over estimate · KV at 8k No measured run |
| RTX 2060 Super NVIDIA · 8 GB VRAM | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Over estimate · KV at 8k No measured run | 17.8 GB Over estimate · KV at 8k No measured run |
Measured runs
| Hardware | Quant | tok/s | Runtime | Source |
|---|---|---|---|---|
| RTX 4090 | Q8 | 52.99 | llama.cpp-based | Source · checked · prefill 3287 |
| Radeon AI Pro R9700 | FP16 (unquantized) | 29.1 | vLLM v0.20.2 ROCm, HIP graphs | Source · checked |
| M3 Pro 18GB | Q4_K_M (4.92 GB, Ollama tag llama3.1:8b) | 27.2 | Ollama 0.40.13 (Metal) | Source · checked |
| NVIDIA GB10 | not stated | 26.4 | NVIDIA NIM 2.0.9, 128K ctx, 1 user | Source · checked |