RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?API pricesVRAM calculatorNew

Can ERNIE 4.5 21B A3B Thinking run on the RTX 5060?

Not fully in VRAM. Even at 2-bit with 8K context, ERNIE 4.5 21B A3B Thinking needs about 8.6 GB, more than the 7.6 GB usable on the RTX 5060. It can still run with offload (slower): Q4_K_M with part of the model in system RAM, about 3.2–6.2 tokens/sec (estimate). Details and command.

Runs with offload (slower)

Runs with offload 4-bit (Q4_K_M) at 8K context: 14 of 28 layers on the RTX 5060 (about 7.0 GB) and the other 14 in system RAM (about 6.4 GB). Needs a PC with at least 32 GB of system RAM. Estimated speed: 3.2–6.2 tokens/sec (slow but usable), versus a bandwidth ceiling of ~34 tok/s if it fit fully in VRAM.

llama-server -hf unsloth/ERNIE-4.5-21B-A3B-Thinking-GGUF:Q4_K_M -c 8192 -ngl 14

Estimate, not a benchmark. The command downloads the GGUF from Hugging Face. The speed range spans dual-channel DDR4-3200 to DDR5-6000 system RAM; your CPU, RAM speed and llama.cpp version move it. If llama.cpp runs out of GPU memory, lower -ngl by 2-3; if VRAM is left over, raise it for more speed. Recent llama.cpp builds can also pick the split automatically. How we estimate offload.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •8.4 GB No8.6 GB No9.9 GB No15.2 GB No—
3-bit (Q3_K_M) •10.6 GB No10.8 GB No12.1 GB No17.4 GB No—
4-bit (Q4_K_M) •13.2 GB No13.5 GB No14.8 GB No20.0 GB No—
5-bit (Q5_K_M) •15.3 GB No15.5 GB No16.9 GB No22.1 GB No—
6-bit (Q6_K) •17.6 GB No17.8 GB No19.1 GB No24.3 GB No—
8-bit (Q8_0) •22.4 GB No22.6 GB No24.0 GB No29.2 GB No—
16-bit (F16/BF16) •41.5 GB No41.7 GB No43.0 GB No48.3 GB No—

• real GGUF file size from unsloth/ERNIE-4.5-21B-A3B-Thinking-GGUF. Speed is a bandwidth ceiling (448 GB/s), not a benchmark. Methodology.

Hardware that does fit it

RTX 3080 10GBRTX 3060 12GBRTX 3080 12GBRTX 4070RTX 4070 SuperRTX 4070 Ti

What fits instead

"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.

More

ERNIE 4.5 21B A3B Thinking on every GPU and Mac · Every model that runs on the RTX 5060 · Other models that fit 8 GB VRAM · Try other settings in the calculator

Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs

Data: Hugging Face Hub (baidu/ERNIE-4.5-21B-A3B-Thinking), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.