Rent a GPU

Can the AMD Radeon AI PRO R9700 run Llama 3.1 70B?

Radeon AI PRO R9700 × Llama 3.1 70B8K context
Yes, with heavy quantizationFits only at a low-quality quant
Memory at Q2_K29.8 GB of 32 GB
Weights 26.5 GBKV cache 2.7 GBRuntime 0.6 GB
QuantQ2_KHeavily degraded
Speed~15tokens per second
Max context13Ktokens that fit at Q2_K
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Only just. Llama 3.1 70B fits on the AMD Radeon AI PRO R9700 at Q2_K, which costs noticeable quality. Expect about 15 tokens/second. A card with more memory is a better experience.

Try other context lengths

Run it with Ollama

Ollama's default llama3.1:70b download is Q4_K_M, which needs about 46.1 GB, more than the 32 GB available. Download the Q2_K GGUF instead (LM Studio lists quants per model), or try a smaller context length.

New to this? Step-by-step setup for the Radeon AI PRO R9700

Run it in the cloud

Want full quality? Run Llama 3.1 70B on a bigger rented GPU.

Rent a cloud GPU by the hour. No upfront cost, stop any time. Not sure whether to rent or buy? Compare the cost.

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 AMD Radeon AI PRO R9700 can use.

QuantQualityMemoryFits?Speed
FP16Full quality144.5 GBToo big—
Q8_0Near-lossless78.3 GBToo big—
Q6_KExcellent61.2 GBToo big—
Q5_K_MVery good53.5 GBToo big—
Q4_K_MGood, most popular46.1 GBToo big—
Q3_K_MNoticeably degraded37.8 GBToo big—
Q2_KHeavily degraded29.8 GBFits~15 tok/s

Measured speed from real Radeon AI PRO R9700 owners

Tokens per second that people measured on their own AMD Radeon AI PRO R9700, next to our estimate.

No one has measured Llama 3.1 70B on the AMD Radeon AI PRO R9700 yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have a Radeon AI PRO R9700? Add your real speed

One command times Llama 3.1 70B in your own Ollama, shows you exactly what it would send, and asks before sending anything. No sign-up, no personal data.

macOS and Linux

curl -fsSL https://gpufit.dev/bench.sh | sh -s -- llama3.1:70b

Windows (PowerShell)

$env:GPUFIT_MODEL="llama3.1:70b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Llama 3.1 70B comfortably

Check Mac Studio M4 Max (64 GB) prices

Models that run well on the AMD Radeon AI PRO R9700

Frequently asked questions

Can AMD Radeon AI PRO R9700 run Llama 3.1 70B?

Only just. Llama 3.1 70B fits on the AMD Radeon AI PRO R9700 at Q2_K, which costs noticeable quality. Expect about 15 tokens/second. A card with more memory is a better experience.

How much VRAM does Llama 3.1 70B need?

About 46.1 GB at Q4_K_M with 8,192 tokens of context, and about 144.5 GB at full FP16 precision.

How fast is Llama 3.1 70B on the AMD Radeon AI PRO R9700?

Roughly 15 tokens per second at Q2_K, estimated from the AMD Radeon AI PRO R9700's 640 GB/s memory bandwidth.