Can the NVIDIA RTX 3080 10GB run Phi-3.5 Mini 3.8B?

RTX 3080 10GB × Phi-3.5 Mini 3.8B8K context
YesRuns fully on the GPU
Memory at Q8_07.9 GB of 10 GB
Weights 4.1 GBKV cache 3.2 GBRuntime 0.6 GB
QuantQ8_0Near-lossless
Memory7.9 GBof 10 GB usable
Speed~112tokens 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 3080 10GB can run Phi-3.5 Mini 3.8B fully in VRAM at Q8_0 (near-lossless), using about 7.9 GB of the 10 GB available, at roughly 112 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 Q8_0, which is near-lossless: pick that GGUF in LM Studio or from Hugging Face.

Run it in the cloud

No NVIDIA RTX 3080 10GB? 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 10 GB the NVIDIA RTX 3080 10GB can use.

QuantQualityMemoryFits?Speed
FP16Full quality11.5 GBToo big—
Q8_0Near-lossless7.9 GBFits~112 tok/s
Q6_KExcellent7 GBFits~146 tok/s
Q5_K_MVery good6.5 GBFits~168 tok/s
Q4_K_MGood, most popular6.1 GBFits~197 tok/s
Q3_K_MNoticeably degraded5.7 GBFits~244 tok/s
Q2_KHeavily degraded5.3 GBFits~318 tok/s

Frequently asked questions

Can NVIDIA RTX 3080 10GB run Phi-3.5 Mini 3.8B?

Yes. The NVIDIA RTX 3080 10GB can run Phi-3.5 Mini 3.8B fully in VRAM at Q8_0 (near-lossless), using about 7.9 GB of the 10 GB available, at roughly 112 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 NVIDIA RTX 3080 10GB?

Roughly 112 tokens per second at Q8_0, estimated from the NVIDIA RTX 3080 10GB's 760 GB/s memory bandwidth.