Can I run Llama 3.2 1B on NVIDIA RTX 3090 24GB?
Yes: Llama 3.2 1B runs on NVIDIA RTX 3090 24GB with F16 at roughly 221 tokens/s. Estimated memory 3.2 GiB at 8,192 tokens of context.
With F16 you can push the context to about 131,072 tokens before memory runs out (F16 KV cache).
Memory by quantisation (8,192-token context)
| Quantisation | Memory | Verdict | Est. speed |
|---|---|---|---|
| F16Unquantized reference | 3.2 GiB | Fits | ~221 tok/s |
| Q8_0Near-lossless | 2.2 GiB | Fits | ~384 tok/s |
| Q6_KVery close to F16 | 1.9 GiB | Fits | ~473 tok/s |
| Q5_K_MGreat quality/size | 1.8 GiB | Fits | ~529 tok/s |
| Q4_K_MBest default for most | 1.6 GiB | Fits | ~596 tok/s |
| IQ4_XSSmaller 4-bit (imatrix) | 1.6 GiB | Fits | ~656 tok/s |
| Q3_K_MNoticeable loss | 1.5 GiB | Fits | ~696 tok/s |
| Q2_KLast resort; big loss | 1.4 GiB | Fits | ~772 tok/s |
NVIDIA RTX 3090 24GB offers about 24 GiB of memory (94% usable for a model) at 936 GB/s. Speed is a bandwidth-bound estimate of single-stream generation at 65% efficiency; real results vary by runtime, drivers and settings, so measure on your machine.
How this is calculated
Weights ≈ parameters × bits per weight ÷ 8. KV cache ≈ 2 × 16 layers × 8 KV heads × 64 head dim × 2 bytes per token. Decode speed ≈ efficiency × memory bandwidth ÷ bytes read per token. Learn the maths in VRAM math and memory bandwidth, or try the VRAM calculator.
Llama 3.2 1B on other hardware
Similar models on NVIDIA RTX 3090 24GB
Running slowly or out of memory? See CUDA out of memory and the quantisation lesson.