DeskGPU
English

Can NVIDIA GeForce RTX 5060 Ti 16GB run gpt-oss-120b?

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

Doesn't fit Even the smallest quantization of gpt-oss-120b (Q2_K) does not fit on one NVIDIA GeForce RTX 5060 Ti 16GB with a context of 8,192 tokens; it needs 62.8 GiB available for “Fits”. 7 identical cards (default even split) are expected to fit. Fewer cards are borderline.

“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): 12.88 GiB per card = 16 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 16 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 5060 Ti 16GB.
Quantization4,0968,19232,768131,072
Q8_0 63.1 GiB Doesn't fit63.3 GiB Doesn't fit64.2 GiB Doesn't fit68.0 GiB Doesn't fit
Q6_K 63.0 GiB Doesn't fit63.2 GiB Doesn't fit64.1 GiB Doesn't fit67.9 GiB Doesn't fit
Q5_K_M 62.8 GiB Doesn't fit63.0 GiB Doesn't fit63.9 GiB Doesn't fit67.7 GiB Doesn't fit
Q4_K_M 62.7 GiB Doesn't fit62.9 GiB Doesn't fit63.8 GiB Doesn't fit67.6 GiB Doesn't fit
Q4_0 62.7 GiB Doesn't fit62.8 GiB Doesn't fit63.7 GiB Doesn't fit67.5 GiB Doesn't fit
Q3_K_M 62.7 GiB Doesn't fit62.8 GiB Doesn't fit63.8 GiB Doesn't fit67.5 GiB Doesn't fit
Q2_K 62.6 GiB Doesn't fit62.8 GiB Doesn't fit63.7 GiB Doesn't fit67.5 GiB Doesn't fit

No speed ceiling is given: the memory bandwidth of NVIDIA GeForce RTX 5060 Ti 16GB is not confirmed by two independent open sources.

Alternatives

Other 16 GB GPUs where gpt-oss-120b fits

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

Largest model of the same family that fits on NVIDIA GeForce RTX 5060 Ti 16GB

Same family: same publisher and the same model name up to the parameter count.

Sources