Can ERNIE 5.5 Flash Base run on the RTX 3060 12GB?
Not fully in VRAM. Even at 2-bit with 8K context, ERNIE 5.5 Flash Base needs about 101 GB, more than the 11.4 GB usable on the RTX 3060 12GB. It can still run with offload (slower): Q3_K_M with part of the model in system RAM. Details and command.
Runs with offload (slower)
Runs with offload 3-bit (Q3_K_M) at 8K context: all attention layers plus the experts of 2 of 43 MoE layers on the RTX 3060 12GB (about 9.0 GB), and the experts of the other 41 layers in system RAM (about 122 GB). Needs a PC with at least 128 GB of system RAM. Speed is not estimated for this model (its active-parameter count is uncertain).
llama-server -m ernie-5-5-flash-base-Q3_K_M.gguf -c 8192 -ngl 999 --n-cpu-moe 41
Estimate, not a benchmark. No GGUF repo was found on Hugging Face yet; point -m at your own GGUF file. 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, raise --n-cpu-moe by 1-2; if VRAM is left over, lower it for more speed. Recent llama.cpp builds can also pick the split automatically. How we estimate offload.
Newer compressed-attention design: long-context figures are an upper bound.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 101 GB No | 101 GB No | 103 GB No | 108 GB No | — |
| 3-bit (Q3_K_M) | 131 GB No | 132 GB No | 133 GB No | 138 GB No | — |
| 4-bit (Q4_K_M) | 164 GB No | 164 GB No | 166 GB No | 171 GB No | — |
| 5-bit (Q5_K_M) | 191 GB No | 191 GB No | 193 GB No | 198 GB No | — |
| 6-bit (Q6_K) | 220 GB No | 220 GB No | 221 GB No | 227 GB No | — |
| 8-bit (Q8_0) | 284 GB No | 284 GB No | 286 GB No | 291 GB No | — |
| 16-bit (F16/BF16) | 534 GB No | 534 GB No | 536 GB No | 541 GB No | — |
• real GGUF file size. Speed is a bandwidth ceiling (360 GB/s), not a benchmark. Methodology.
Hardware that does fit it
DGX SparkRyzen AI Max+ 395 128GBH200Mac M2 Ultra 192GBMac M3 Ultra 256GBMac M3 Ultra 512GB
What fits instead
- Cheapest listed GPU that runs ERNIE 5.5 Flash Base: DGX Spark (128 GB, launch MSRP $3,999) at Q2_K, fully in VRAM at 8K context.
- Largest popular model that fits the RTX 3060 12GB: Qwen3.5 9B (9.7B) at Q8_0, about 10.0 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 5.5 Flash Base on every GPU and Mac · Every model that runs on the RTX 3060 12GB · Other models that fit 12 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (baidu/ERNIE-5.5-Flash-Base), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.