DeskGPU
English

Can AMD Radeon RX 7900 XTX run Devstral-Small-2-24B-Instruct-2512?

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, Devstral-Small-2-24B-Instruct-2512 fits on AMD Radeon RX 7900 XTX at Q6_K with a context of 8,192 tokens. One card needs 21.0 GiB available for “Fits”.

At Q6_K, the longest context that fits is 18,688 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 46.8 GiB Doesn't fit47.5 GiB Doesn't fit51.5 GiB Doesn't fit67.5 GiB Doesn't fit
Q8_0 25.8 GiB Tight26.5 GiB Tight30.4 GiB Doesn't fit46.4 GiB Doesn't fit
Q6_K 20.3 GiB Fits21.0 GiB Fits25.0 GiB Tight41.0 GiB Doesn't fit
Q5_K_M 17.9 GiB Fits18.6 GiB Fits22.6 GiB Fits38.6 GiB Doesn't fit
Q4_K_M 15.6 GiB Fits16.3 GiB Fits20.3 GiB Fits36.3 GiB Doesn't fit
Q4_0 14.8 GiB Fits15.4 GiB Fits19.4 GiB Fits35.4 GiB Doesn't fit
IQ4_XS 14.1 GiB Fits14.7 GiB Fits18.7 GiB Fits34.7 GiB Doesn't fit
Q3_K_M 12.9 GiB Fits13.6 GiB Fits17.6 GiB Fits33.5 GiB Doesn't fit
Q2_K 10.4 GiB Fits11.1 GiB Fits15.1 GiB Fits31.1 GiB Doesn't fit

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 Devstral-Small-2-24B-Instruct-2512 fits

Sources