DeskGPU
English

Can AMD Radeon RX 7900 XTX run NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16?

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

Fits By llama.cpp’s default load check, NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 fits on AMD Radeon RX 7900 XTX at Q4_0 with a context of 8,192 tokens. One card needs 19.3 GiB available for “Fits”.

At Q4_0, the longest context that fits is 262,144 tokens.

“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, ROCm back end on Linux (AMD 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): 22.75 GiB per card = 24 GiB nominal − 16 MiB (nominal minus the total that llama.cpp reported for this GPU in public logs) − 1,216 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 apply to the configuration seen in public logs, where llama.cpp reported 24,560 MiB of total memory for this GPU. 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 24 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 AMD Radeon RX 7900 XTX.
Quantization4,0968,19232,768131,072
BF16 62.7 GiB Doesn't fit62.8 GiB Doesn't fit63.0 GiB Doesn't fit63.8 GiB Doesn't fit
Q8_0 34.0 GiB Doesn't fit34.1 GiB Doesn't fit34.3 GiB Doesn't fit35.1 GiB Doesn't fit
Q6_K 34.0 GiB Doesn't fit34.0 GiB Doesn't fit34.2 GiB Doesn't fit35.0 GiB Doesn't fit
Q5_K_M 26.9 GiB Tight27.0 GiB Tight27.2 GiB Tight27.9 GiB Tight
Q4_K_M 25.5 GiB Tight25.5 GiB Tight25.7 GiB Tight26.5 GiB Tight
Q4_0 19.2 GiB Fits19.3 GiB Fits19.5 GiB Fits20.3 GiB Fits
IQ4_XS 19.1 GiB Fits19.1 GiB Fits19.3 GiB Fits20.1 GiB Fits
Q3_K_M 20.0 GiB Fits20.0 GiB Fits20.2 GiB Fits21.0 GiB Fits
Q2_K 19.1 GiB Fits19.1 GiB Fits19.3 GiB Fits20.1 GiB Fits
IQ2_M 19.0 GiB Fits19.1 GiB Fits19.3 GiB Fits20.1 GiB Fits

No speed ceiling is given: the memory bandwidth of AMD Radeon RX 7900 XTX is not confirmed by two independent open sources.

Alternatives

Other 24 GB GPUs where NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 fits

Sources