RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Qwen2.5 1.5B Instruct run on the RX 9070?

Yes. At 8K context the best fit is F16, using about 3.8 GB of the 15.2 GB usable on the RX 9070. Estimated speed ceiling: ~207 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •1.5 GB Fits1.6 GB Fits2.3 GB Fits850
3-bit (Q3_K_M) •1.7 GB Fits1.8 GB Fits2.4 GB Fits692
4-bit (Q4_K_M) •1.8 GB Fits1.9 GB Fits2.6 GB Fits573
5-bit (Q5_K_M) •2.0 GB Fits2.1 GB Fits2.8 GB Fits498
6-bit (Q6_K) •2.2 GB Fits2.3 GB Fits2.9 GB Fits437
8-bit (Q8_0) •2.6 GB Fits2.7 GB Fits3.3 GB Fits338
16-bit (F16/BF16)3.7 GB Fits3.8 GB Fits4.4 GB Fits207

• real GGUF file size from Qwen/Qwen2.5-1.5B-Instruct-GGUF. Speed is a bandwidth ceiling (640 GB/s), not a benchmark. Methodology.

More

Qwen2.5 1.5B Instruct on every GPU and Mac · Every model that runs on the RX 9070 · Other models that fit 16 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (Qwen/Qwen2.5-1.5B-Instruct), AMD specs. Model data last checked 2026-11-17; refreshed hourly.