ERNIE 21B A3B Thinking Gemini 3 Pro High Reasoning V2 needs about 14.2 GB of memory at Q4_K_M (a 13.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 24 quants, from 0.0 GB to 17.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
ERNIE 21B A3B Thinking Gemini 3 Pro High Reasoning V2 – large‑context reasoning model
ERNIE 21B A3B Thinking Gemini 3 Pro High Reasoning V2 is a 21.8B parameter model with 3B active mixture‑of‑experts. It supports 131072 token context and is licensed under apache‑2.0. The model excels in detailed reasoning and creative prose.
Good at
- Detailed reasoning
- Creative brainstorming
- Long‑context dialogue
Limits
- No vision support
- Requires high VRAM for large quants
- No GPU acceleration beyond llama.cpp
Best for
- Complex problem solving
- Technical documentation generation
- Creative writing assistance
Who it’s for. Developers and researchers needing a large‑context reasoning model for text‑only tasks. The model is uncensored and suitable for local deployment on Linux with llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.0 GB | Fits | Get file → | |
| IQ1_S | 4.5 GB | 5.4 GB | Fits | Get file → | |
| IQ1_M | 5.0 GB | 5.9 GB | Fits | Get file → | |
| IQ2_XXS | 5.8 GB | 6.8 GB | Fits | Get file → | |
| IQ2_XS | 6.5 GB | 7.4 GB | Tight | Get file → | |
| IQ2_S | 6.5 GB | 7.5 GB | Tight | Get file → | |
| IQ2_M | 7.2 GB | 8.1 GB | Too big | Get file → | |
| Q2_K_S | 7.4 GB | 8.4 GB | Too big | Get file → | |
| Q2_K | 8.1 GB | 9.0 GB | Too big | Get file → | |
| IQ3_XXS | 8.5 GB | 9.4 GB | Too big | Get file → | |
| IQ3_XS | 9.0 GB | 10.0 GB | Too big | Get file → | |
| Q3_K_S | 9.5 GB | 10.5 GB | Too big | Get file → | |
| IQ3_S | 9.5 GB | 10.5 GB | Too big | Get file → | |
| IQ3_M | 9.6 GB | 10.6 GB | Too big | Get file → | |
| Q3_K_M | 10.5 GB | 11.4 GB | Too big | Get file → | |
| Q3_K_L | 11.4 GB | 12.3 GB | Too big | Get file → | |
| IQ4_XS | 11.7 GB | 12.7 GB | Too big | Get file → | |
| Q4_0 | 12.4 GB | 13.4 GB | Too big | Get file → | |
| Q4_K_S | 12.4 GB | 13.4 GB | Too big | Get file → | |
| Q4_K_M | 13.2 GB | 14.2 GB | Too big | Get file → | |
| Q4_1 | 13.7 GB | 14.7 GB | Too big | Get file → | |
| Q5_K_S | 15.1 GB | 16.0 GB | Too big | Get file → | |
| Q5_K_M | 15.5 GB | 16.5 GB | Too big | Get file → | |
| Q6_K | 17.9 GB | 18.9 GB | Too big | Get file → |
For 8 GB VRAM use IQ1_S (file size 4.48 GB, memory 5.4 GB). For 12 GB VRAM use Q4_K_M (file size 13.25 GB, memory 14.2 GB). For 16 GB VRAM use Q5_K_M (file size 15.51 GB, memory 16.5 GB). Estimates are approximate.
What GPU do you need for ERNIE 21B A3B Thinking Gemini 3 Pro High Reasoning V2?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.0 GB in use).
- 6 GB VRAM: the best quant that fits is IQ1_M (5.0 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is IQ2_S (6.5 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q3_K_M (10.5 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_S (15.1 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (17.9 GB file, about 18.9 GB in use).
Which ERNIE 21B A3B Thinking Gemini 3 Pro High Reasoning V2 quant should you choose?
Q4_K_M is the usual starting point for ERNIE 21B A3B Thinking Gemini 3 Pro High Reasoning V2: it balances file size and quality well. Here it is a 13.2 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about ERNIE 21B A3B Thinking Gemini 3 Pro High Reasoning V2
How much VRAM does ERNIE 21B A3B Thinking Gemini 3 Pro High Reasoning V2 need?
About 14.2 GB at Q4_K_M with an 8K context window. That is the 13.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run ERNIE 21B A3B Thinking Gemini 3 Pro High Reasoning V2 on an 8 GB GPU?
Yes, with IQ2_S: the 6.5 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of ERNIE 21B A3B Thinking Gemini 3 Pro High Reasoning V2 GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 4.5 GB, IQ1_M is 5.0 GB, IQ2_XXS is 5.8 GB, IQ2_XS is 6.5 GB, IQ2_S is 6.5 GB and 18 more.
What context length does ERNIE 21B A3B Thinking Gemini 3 Pro High Reasoning V2 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download ERNIE 21B A3B Thinking Gemini 3 Pro High Reasoning V2 GGUF?
The files are on Hugging Face in the mradermacher/ERNIE-21B-A3B-Thinking-Gemini-3-Pro-High-Reasoning-V2-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does ERNIE 21B A3B Thinking Gemini 3 Pro High Reasoning V2 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
Yes, use the IQ1_S quant which requires about 5.4 GB of VRAM at 8k context.
Does this model support image inputs?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the apache‑2.0 license.