Can the AMD Radeon RX 7800 XT run Phi-3.5 Mini 3.8B?

Radeon RX 7800 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
Memory11.5 GBof 16 GB usable
Speed~49tokens 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 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 49 tokens/second.

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.

Run it in the cloud

No AMD Radeon RX 7800 XT? Run Phi-3.5 Mini 3.8B in the cloud.

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

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 quality11.5 GBFits~49 tok/s
Q8_0Near-lossless7.9 GBFits~92 tok/s
Q6_KExcellent7 GBFits~120 tok/s
Q5_K_MVery good6.5 GBFits~138 tok/s
Q4_K_MGood, most popular6.1 GBFits~162 tok/s
Q3_K_MNoticeably degraded5.7 GBFits~201 tok/s
Q2_KHeavily degraded5.3 GBFits~261 tok/s

Frequently asked questions

Can AMD Radeon RX 7800 XT run Phi-3.5 Mini 3.8B?

Yes. The AMD Radeon RX 7800 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 49 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 7800 XT?

Roughly 49 tokens per second at FP16, estimated from the AMD Radeon RX 7800 XT's 624 GB/s memory bandwidth.