RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Kimi VL A3B Instruct run on the RX 7900 GRE?

Yes. At 8K context the best fit is Q5_K_M, using about 12.2 GB of the 15.2 GB usable on the RX 7900 GRE. Estimated speed ceiling: ~262 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •7.0 GB Fits7.1 GB Fits7.8 GB Fits10.6 GB Fits479
3-bit (Q3_K_M) •8.6 GB Fits8.7 GB Fits9.4 GB Fits12.2 GB Fits380
4-bit (Q4_K_M) •10.6 GB Fits10.8 GB Fits11.5 GB Fits14.3 GB Tight299
5-bit (Q5_K_M) •12.0 GB Fits12.2 GB Fits12.9 GB Fits15.7 GB No262
6-bit (Q6_K) •14.1 GB Tight14.2 GB Tight15.0 GB Tight17.8 GB No221
8-bit (Q8_0) •16.6 GB No16.8 GB No17.5 GB No20.3 GB No—
16-bit (F16/BF16)31.4 GB No31.5 GB No32.2 GB No35.1 GB No—

• real GGUF file size from mradermacher/Kimi-VL-A3B-Instruct-GGUF. Speed is a bandwidth ceiling (576 GB/s), not a benchmark. Methodology.

More

Kimi VL A3B Instruct on every GPU and Mac · Every model that runs on the RX 7900 GRE · Other models that fit 16 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (moonshotai/Kimi-VL-A3B-Instruct), AMD specs. Data as of 2026-11-17.