Gemma 4 21b A4B It REAP Heretic needs about 22.4 GB of memory at Q4_K_M (a 13.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 18.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Gemma 4 21b A4B It REAP Heretic – 20.8B parameter model with 4B active experts
Gemma 4 21b A4B It REAP Heretic is a 20.8B parameter model with 4B active parameters per token. It is a mixture of experts with 128 experts per layer, 20% of which have been pruned using REAP. The model supports a context length of 262144 tokens.
Good at
- Coding tasks
- Reasoning and math
- Tool‑calling
Limits
- No vision support
- Requires large VRAM for full precision
- License is gemma
Best for
- Developers building code assistants
- Researchers testing large‑scale MoE models
- Applications needing long‑context reasoning
Who it’s for. Engineers and researchers who need a large‑parameter, long‑context model with expert pruning. The model is suitable for local deployment with sufficient GPU memory and a compatible GGUF runtime.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 8.6 GB | Too big | Get file → | |
| IQ1_S | 6.9 GB | 15.4 GB | Too big | Get file → | |
| IQ1_M | 7.2 GB | 15.7 GB | Too big | Get file → | |
| IQ2_XXS | 7.7 GB | 16.2 GB | Too big | Get file → | |
| IQ2_XS | 8.1 GB | 16.7 GB | Too big | Get file → | |
| IQ2_S | 8.2 GB | 16.7 GB | Too big | Get file → | |
| IQ2_M | 8.6 GB | 17.1 GB | Too big | Get file → | |
| Q2_K | 8.8 GB | 17.3 GB | Too big | Get file → | |
| Q2_K_S | 8.8 GB | 17.3 GB | Too big | Get file → | |
| IQ3_XXS | 9.3 GB | 17.9 GB | Too big | Get file → | |
| IQ3_XS | 9.6 GB | 18.2 GB | Too big | Get file → | |
| IQ3_S | 10.1 GB | 18.7 GB | Too big | Get file → | |
| Q3_K_S | 10.1 GB | 18.7 GB | Too big | Get file → | |
| IQ3_M | 10.3 GB | 18.8 GB | Too big | Get file → | |
| Q3_K_M | 11.0 GB | 19.5 GB | Too big | Get file → | |
| Q3_K_L | 11.4 GB | 20.0 GB | Too big | Get file → | |
| IQ4_XS | 11.5 GB | 20.0 GB | Too big | Get file → | |
| Q4_0 | 12.0 GB | 20.5 GB | Too big | Get file → | |
| Q4_K_S | 12.8 GB | 21.3 GB | Too big | Get file → | |
| Q4_1 | 13.2 GB | 21.7 GB | Too big | Get file → | |
| Q4_K_M | 13.8 GB | 22.4 GB | Too big | Get file → | |
| Q5_K_S | 14.8 GB | 23.4 GB | Too big | Get file → | |
| Q5_K_M | 15.7 GB | 24.3 GB | Too big | Get file → | |
| Q6_K | 18.6 GB | 27.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (file size 6.86 GB, memory 15.4 GB at 8 k context). For 12 GB VRAM, IQ2_XS (file size 8.11 GB, memory 16.7 GB). For 16 GB VRAM, Q4_K_M (file size 13.83 GB, memory 22.4 GB). Estimates are approximate.
What GPU do you need for Gemma 4 21b A4B It REAP Heretic?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 8.6 GB in use).
- 16 GB VRAM: the best quant that fits is IQ1_M (7.2 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_S (14.8 GB file, about 23.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (18.6 GB file, about 27.2 GB in use).
Which Gemma 4 21b A4B It REAP Heretic quant should you choose?
Q4_K_M is the usual starting point for Gemma 4 21b A4B It REAP Heretic: it balances file size and quality well. Here it is a 13.8 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 Gemma 4 21b A4B It REAP Heretic
How much VRAM does Gemma 4 21b A4B It REAP Heretic need?
About 22.4 GB at Q4_K_M with an 8K context window. That is the 13.8 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 Gemma 4 21b A4B It REAP Heretic on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma 4 21b A4B It REAP Heretic GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 6.9 GB, IQ1_M is 7.2 GB, IQ2_XXS is 7.7 GB, IQ2_XS is 8.1 GB, IQ2_S is 8.2 GB and 18 more.
What context length does Gemma 4 21b A4B It REAP Heretic support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 8.1 GB at 8K and 32.2 GB at 32K.
Where can I download Gemma 4 21b A4B It REAP Heretic GGUF?
The files are on Hugging Face in the mradermacher/gemma-4-21b-a4b-it-REAP-heretic-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 Gemma 4 21b A4B It REAP Heretic use?
Hugging Face lists the license as gemma. 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?
The smallest quant that fits 8 GB VRAM is IQ1_S, which uses 15.4 GB of memory at 8 k context. It will not run fully on 8 GB VRAM without off‑loading.
Does this model support vision?
No, the model is a text‑only model. Vision files are not provided.
What is the context length of this model?
The model supports a context length of 262144 tokens.