Can an AMD Radeon RX 9070 XT run gemma-4-26B-A4B-it?
Yes, with CPU offload. gemma-4-26B-A4B-it needs 19.0GB at MXFP4_MOE with llama.cpp and 8K context; the AMD Radeon RX 9070 XT has 16GB of VRAM (15.5GB usable), so part of the model spills to system RAM — it loads, but expect the interactive speed tier.
AMD Radeon RX 9070 XT · gemma-4-26B-A4B-it · MXFP4_MOE
⚠️ Tight — grade C
InteractivebetaHybrid attention — KV computed as full-cache upper bound · MoE speed estimate — wide error bars · CPU offload — speed varies heavily with layer split · ROCm/Vulkan performance not yet calibrated
weights 16.6 GBKV cache 2.01 GBoverhead 0.44 GBpool 15.5 GBneeds 19.0 GB — spills to system RAM
assumes llama.cpp · batch 1 · 8K context · fp16 KV cache · 64GB system RAM (CPU offload)
$599 MSRP · as of 2026-07-08
Affiliate link — we may earn a commission. Verdicts are computed before any link is attached.
Every quant, graded
AMD Radeon RX 9070 XT × gemma-4-26B-A4B-it, llama.cpp, 8K context.
| Quant | File size | Fit | Speed tier |
|---|---|---|---|
| Q8_0 | 26.9 GB | Tight · C | interactive · offload · beta |
| UD-Q5_K_M | 21.1 GB | Tight · C | interactive · offload · beta |
| UD-Q4_K_M | 16.9 GB | Tight · C | interactive · offload · beta |
| MXFP4_MOE | 16.6 GB | Tight · C | interactive · offload · beta |
gemma-4-26B-A4B-it on similar hardware
More models on the AMD Radeon RX 9070 XT
Verdict computed from published specs and measured GGUF file sizes — see how the math works.