Can AMD Radeon RX 7900 XT run gemma-3-27b-it?

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, gemma-3-27b-it fits on AMD Radeon RX 7900 XT at IQ4_XS with a context of 8,192 tokens. One card needs 18.6 GiB available for “Fits”.

At IQ4_XS, the longest context that fits is 8,192 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): 18.63 GiB per card = 20 GiB nominal − 144 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) − 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 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 20 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 XT.
Quantization	4,096	8,192	32,768	131,072
BF16	56.5 GiB Doesn't fit	57.1 GiB Doesn't fit	59.1 GiB Doesn't fit	67.2 GiB Doesn't fit
Q8_0	31.7 GiB Doesn't fit	32.3 GiB Doesn't fit	34.3 GiB Doesn't fit	42.4 GiB Doesn't fit
Q6_K	25.3 GiB Doesn't fit	25.9 GiB Doesn't fit	27.9 GiB Doesn't fit	36.0 GiB Doesn't fit
Q5_K_M	22.5 GiB Tight	23.0 GiB Tight	25.0 GiB Tight	33.1 GiB Doesn't fit
Q4_K_M	19.8 GiB Tight	20.3 GiB Tight	22.4 GiB Tight	30.5 GiB Doesn't fit
Q4_0	18.9 GiB Tight	19.4 GiB Tight	21.5 GiB Tight	29.6 GiB Doesn't fit
IQ4_XS	18.1 GiB Fits	18.6 GiB Fits	20.6 GiB Tight	28.7 GiB Doesn't fit
Q3_K_M	16.7 GiB Fits	17.3 GiB Fits	19.3 GiB Tight	27.4 GiB Doesn't fit
Q2_K	13.9 GiB Fits	14.4 GiB Fits	16.4 GiB Fits	24.5 GiB Tight

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

Alternatives

Other 20 GB GPUs where gemma-3-27b-it fits

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

Sources

Model page, with every quantization and its files: gemma-3-27b-it
GPU page, with each specification and its sources: AMD Radeon RX 7900 XT
Model files on Hugging Face (pinned revisions): google/gemma-3-27b-it@005ad34, unsloth/gemma-3-27b-it-GGUF@7cd0121
Memory size of AMD Radeon RX 7900 XT from: Wikipedia: Radeon RX 7000 series (CC BY-SA 4.0), ROCm documentation gpu-specs.rst (MIT)
Methodology