DeskGPU
English

Can AMD Radeon RX 7900 XT run GLM-4.7-Flash?

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, GLM-4.7-Flash fits on AMD Radeon RX 7900 XT at Q4_0 with a context of 8,192 tokens. One card needs 18.5 GiB available for “Fits”.

At Q4_0, the longest context that fits is 11,008 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.
Quantization4,0968,19232,768131,072
BF16 59.6 GiB Doesn't fit59.9 GiB Doesn't fit61.2 GiB Doesn't fit66.6 GiB Doesn't fit
Q8_0 32.4 GiB Doesn't fit32.6 GiB Doesn't fit34.0 GiB Doesn't fit39.4 GiB Doesn't fit
Q6_K 25.5 GiB Doesn't fit25.7 GiB Doesn't fit27.1 GiB Doesn't fit32.5 GiB Doesn't fit
Q5_K_M 22.3 GiB Tight22.5 GiB Tight23.9 GiB Tight29.3 GiB Doesn't fit
Q4_K_M 19.3 GiB Tight19.5 GiB Tight20.9 GiB Tight26.3 GiB Doesn't fit
Q4_0 18.2 GiB Fits18.5 GiB Fits19.8 GiB Tight25.2 GiB Doesn't fit
IQ4_XS 17.3 GiB Fits17.5 GiB Fits18.9 GiB Tight24.3 GiB Doesn't fit
Q3_K_M 15.7 GiB Fits15.9 GiB Fits17.3 GiB Fits22.7 GiB Tight
Q2_K 12.5 GiB Fits12.8 GiB Fits14.1 GiB Fits19.5 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 GLM-4.7-Flash fits

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

Sources