DeskGPU
English

Can NVIDIA GeForce RTX 3080 10GB run phi-4?

This page was written and translated automatically by AI and checked by software against its sources, with no human editing. Specifications come from the sources listed; memory requirements and speeds are estimates calculated with published formulas. How we use AI

Tight No quantization of phi-4 clearly fits on NVIDIA GeForce RTX 3080 10GB with a context of 8,192 tokens. The highest borderline one is Q4_K_M, which needs 11.4 GiB available for “Fits”; that is within the estimate error range.

“Fits” means llama.cpp's default --fit load check would place all layers on the GPU: our estimate of llama.cpp's buffers, plus its error margin, plus llama.cpp's 1 GiB per-card reserve, is within the memory counted as available. It does not promise that peak memory while generating fits. How results are decided

Values updated Oct 19, 2026 · Calculator

Run profile: llama.cpp, CUDA back end (NVIDIA discrete GPU), all layers on the GPU, Flash Attention on, micro-batch (-ub) 512, F16 KV cache, context (-c) as shown; “Fits” is judged with llama-server’s default 4 parallel sequences (-np auto, unified KV cache) and “Doesn’t fit” with 1 sequence; idle GPU with no other programs using its memory.

Memory counted as available for “Fits” (C_low): 6.88 GiB per card = 10 GiB nominal − 1,054 MiB (the largest gap between nominal and reported total measured on consumer and workstation GPUs in this profile, used because no public log reports this GPU’s own total) − 2,112 MiB (the largest start-up and runtime use seen in this profile’s public logs), rounded down to a multiple of 64 MiB.

These results assume the card’s default configuration. Settings that reduce usable memory (for example ECC, where the card supports it) are not covered.

Memory used for “Doesn’t fit” (C_high): the full 10 GiB per card. Run profiles and their measurements

Memory needed by quantization and context

Available memory needed for “Fits” (X, GiB per card) and the result on NVIDIA GeForce RTX 3080 10GB.
Quantization4,0968,192
F16 29.8 GiB Doesn't fit30.7 GiB Doesn't fit
Q8_0 16.8 GiB Doesn't fit17.7 GiB Doesn't fit
Q6_K 13.5 GiB Doesn't fit14.3 GiB Doesn't fit
Q5_K_M 12.0 GiB Tight12.8 GiB Doesn't fit
Q4_K_M 10.5 GiB Tight11.4 GiB Tight
Q3_K_M 8.9 GiB Tight9.8 GiB Tight
Q2_K 7.4 GiB Tight8.3 GiB Tight

Alternatives

Other 10 GB GPUs where phi-4 fits

No other GPU with the same memory size fits this model.

Sources