Rent a GPU

Can the AMD Radeon RX 9070 XT run Phi-3.5 Mini 3.8B?

Radeon RX 9070 XT × Phi-3.5 Mini 3.8B8K context
YesRuns fully on the GPU
Memory at FP1611.5 GB of 16 GB
Weights 7.6 GBKV cache 3.2 GBRuntime 0.6 GB
QuantFP16Full quality
Speed~50tokens per second
Max context18Ktokens that fit at FP16
  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 9070 XT can run Phi-3.5 Mini 3.8B fully in VRAM at FP16 (full quality), using about 11.5 GB of the 16 GB available, at roughly 50 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Phi-3.5 Mini 3.8B:

ollama run phi3.5:3.8b

Ollama's default download is Q4_K_M (about 6.1 GB here). You have room for FP16, which is full quality: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the Radeon RX 9070 XT

Run it in the cloud

No AMD Radeon RX 9070 XT? Run Phi-3.5 Mini 3.8B 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 9070 XT can use.

QuantQualityMemoryFits?Speed
FP16Full quality11.5 GBFits~50 tok/s
Q8_0Near-lossless7.9 GBFits~95 tok/s
Q6_KExcellent7 GBFits~123 tok/s
Q5_K_MVery good6.5 GBFits~141 tok/s
Q4_K_MGood, most popular6.1 GBFits~166 tok/s
Q3_K_MNoticeably degraded5.7 GBFits~206 tok/s
Q2_KHeavily degraded5.3 GBFits~268 tok/s

Measured speed from real Radeon RX 9070 XT owners

Tokens per second that people measured on their own AMD Radeon RX 9070 XT, next to our estimate.

No one has measured Phi-3.5 Mini 3.8B on the AMD Radeon RX 9070 XT yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have a Radeon RX 9070 XT? Add your real speed

One command times Phi-3.5 Mini 3.8B 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 -- phi3.5:3.8b

Windows (PowerShell)

$env:GPUFIT_MODEL="phi3.5:3.8b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Phi-3.5 Mini 3.8B comfortably

Models that run well on the AMD Radeon RX 9070 XT

Frequently asked questions

Can AMD Radeon RX 9070 XT run Phi-3.5 Mini 3.8B?

Yes. The AMD Radeon RX 9070 XT can run Phi-3.5 Mini 3.8B fully in VRAM at FP16 (full quality), using about 11.5 GB of the 16 GB available, at roughly 50 tokens/second.

How much VRAM does Phi-3.5 Mini 3.8B need?

About 6.1 GB at Q4_K_M with 8,192 tokens of context, and about 11.5 GB at full FP16 precision.

How fast is Phi-3.5 Mini 3.8B on the AMD Radeon RX 9070 XT?

Roughly 50 tokens per second at FP16, estimated from the AMD Radeon RX 9070 XT's 640 GB/s memory bandwidth.