Rent a GPU

Can the NVIDIA RTX 5090 run Llama 3.2 3B?

RTX 5090 × Llama 3.2 3B8K context
YesRuns fully on the GPU
Memory at FP168 GB of 32 GB
Weights 6.4 GBKV cache 0.9 GBRuntime 0.6 GB
QuantFP16Full quality
Memory8 GBof 32 GB usable
Speed~167tokens per second
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Yes. The NVIDIA RTX 5090 can run Llama 3.2 3B fully in VRAM at FP16 (full quality), using about 8 GB of the 32 GB available, at roughly 167 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Llama 3.2 3B:

ollama run llama3.2:3b

Ollama's default download is Q4_K_M (about 3.5 GB here). You have room for FP16, which is full quality: pick that GGUF in LM Studio or from Hugging Face.

Run it in the cloud

No NVIDIA RTX 5090? Run Llama 3.2 3B in the cloud.

Rent a cloud GPU by the hour. No upfront cost, stop any time.

Rent a GPU on RunPodRent a GPU on Vast.ai

Memory needed by quantization

At 8,192 tokens of context. The black line marks the 32 GB the NVIDIA RTX 5090 can use.

QuantQualityMemoryFits?Speed
FP16Full quality8 GBFits~167 tok/s
Q8_0Near-lossless5 GBFits~315 tok/s
Q6_KExcellent4.2 GBFits~408 tok/s
Q5_K_MVery good3.8 GBFits~471 tok/s
Q4_K_MGood, most popular3.5 GBFits~553 tok/s
Q3_K_MNoticeably degraded3.1 GBFits~685 tok/s
Q2_KHeavily degraded2.7 GBFits~893 tok/s

GPUs that run Llama 3.2 3B comfortably

Models that run well on the NVIDIA RTX 5090

Frequently asked questions

Can NVIDIA RTX 5090 run Llama 3.2 3B?

Yes. The NVIDIA RTX 5090 can run Llama 3.2 3B fully in VRAM at FP16 (full quality), using about 8 GB of the 32 GB available, at roughly 167 tokens/second.

How much VRAM does Llama 3.2 3B need?

About 3.5 GB at Q4_K_M with 8,192 tokens of context, and about 8 GB at full FP16 precision.

How fast is Llama 3.2 3B on the NVIDIA RTX 5090?

Roughly 167 tokens per second at FP16, estimated from the NVIDIA RTX 5090's 1792 GB/s memory bandwidth.