Can ERNIE 4.5 21B A3B Thinking run on the RTX 3090?
Yes. At 8K context the best fit is Q6_K, using about 17.8 GB of the 22.8 GB usable on the RTX 3090. Estimated speed ceiling: ~52 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 8.4 GB Fits | 8.6 GB Fits | 9.9 GB Fits | 15.2 GB Fits | 115 |
| 3-bit (Q3_K_M) • | 10.6 GB Fits | 10.8 GB Fits | 12.1 GB Fits | 17.4 GB Fits | 89 |
| 4-bit (Q4_K_M) • | 13.2 GB Fits | 13.5 GB Fits | 14.8 GB Fits | 20.0 GB Fits | 70 |
| 5-bit (Q5_K_M) • | 15.3 GB Fits | 15.5 GB Fits | 16.9 GB Fits | 22.1 GB Tight | 60 |
| 6-bit (Q6_K) • | 17.6 GB Fits | 17.8 GB Fits | 19.1 GB Fits | 24.3 GB No | 52 |
| 8-bit (Q8_0) • | 22.4 GB Tight | 22.6 GB Tight | 24.0 GB No | 29.2 GB No | 40 |
| 16-bit (F16/BF16) • | 41.5 GB No | 41.7 GB No | 43.0 GB No | 48.3 GB No | — |
• real GGUF file size from unsloth/ERNIE-4.5-21B-A3B-Thinking-GGUF. Speed is a bandwidth ceiling (936 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs ERNIE 4.5 21B A3B Thinking: Arc A770 16GB (16 GB, launch MSRP $349) at Q4_K_M, fully in VRAM at 8K context.
- Largest popular model that fits the RTX 3090: Gemma 4 31B IT (31B) at Q4_K_M, about 20.0 GB at 8K context.
"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 3090 · Other models that fit 24 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.