Rent a GPU

Can the AMD Radeon RX 7800 XT run Llama 3.2 1B?

Radeon RX 7800 XT × Llama 3.2 1B8K context
YesRuns fully on the GPU
Memory at FP163.3 GB of 16 GB
Weights 2.5 GBKV cache 0.3 GBRuntime 0.6 GB
QuantFP16Full quality
Memory3.3 GBof 16 GB usable
Speed~151tokens 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 AMD Radeon RX 7800 XT can run Llama 3.2 1B fully in VRAM at FP16 (full quality), using about 3.3 GB of the 16 GB available, at roughly 151 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Llama 3.2 1B:

ollama run llama3.2:1b

Ollama's default download is Q4_K_M (about 1.6 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 AMD Radeon RX 7800 XT? Run Llama 3.2 1B 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 16 GB the AMD Radeon RX 7800 XT can use.

QuantQualityMemoryFits?Speed
FP16Full quality3.3 GBFits~151 tok/s
Q8_0Near-lossless2.2 GBFits~284 tok/s
Q6_KExcellent1.9 GBFits~368 tok/s
Q5_K_MVery good1.8 GBFits~425 tok/s
Q4_K_MGood, most popular1.6 GBFits~498 tok/s
Q3_K_MNoticeably degraded1.5 GBFits~618 tok/s
Q2_KHeavily degraded1.3 GBFits~805 tok/s

GPUs that run Llama 3.2 1B comfortably

Models that run well on the AMD Radeon RX 7800 XT

Frequently asked questions

Can AMD Radeon RX 7800 XT run Llama 3.2 1B?

Yes. The AMD Radeon RX 7800 XT can run Llama 3.2 1B fully in VRAM at FP16 (full quality), using about 3.3 GB of the 16 GB available, at roughly 151 tokens/second.

How much VRAM does Llama 3.2 1B need?

About 1.6 GB at Q4_K_M with 8,192 tokens of context, and about 3.3 GB at full FP16 precision.

How fast is Llama 3.2 1B on the AMD Radeon RX 7800 XT?

Roughly 151 tokens per second at FP16, estimated from the AMD Radeon RX 7800 XT's 624 GB/s memory bandwidth.