Gemma 4 64E A4B Heretic needs about 17.8 GB of memory at Q4_K_M (a 9.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 5.9 GB (Q2_K) to 14.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Gemma 4 64E A4B Heretic – 13.8B parameters, 262144 token context
Gemma 4 64E A4B Heretic is a 13.8B parameter model with 262144 trained context tokens. It is a mixture of experts with 4 active parameters. The model excels at following instructions and roleplaying but has limited math accuracy.
Good at
- Instruction following
- Roleplaying
- Reasoning
Limits
- Math accuracy is poor
- No vision support by default
- License not specified
Best for
- Chat assistants
- Narrative generation
- Creative roleplay
Who it’s for. Developers and researchers looking for a large Gemma model with a long context window and expert mixing. The model is suitable for applications that require detailed instruction following and roleplay, but not for precise mathematical calculations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 5.9 GB | 14.5 GB | Too big | Get file → | |
| Q3_K_S | 6.8 GB | 15.3 GB | Too big | Get file → | |
| Q3_K_M | 7.4 GB | 15.9 GB | Too big | Get file → | |
| Q3_K_L | 7.7 GB | 16.2 GB | Too big | Get file → | |
| IQ4_XS | 7.8 GB | 16.3 GB | Too big | Get file → | |
| Q4_K_S | 8.5 GB | 17.1 GB | Too big | Get file → | |
| Q4_K_M | 9.2 GB | 17.8 GB | Too big | Get file → | |
| Q5_K_S | 9.9 GB | 18.4 GB | Too big | Get file → | |
| Q5_K_M | 10.5 GB | 19.0 GB | Too big | Get file → | |
| Q6_K | 12.3 GB | 20.9 GB | Too big | Get file → | |
| Q8_0 | 14.7 GB | 23.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_S (8.52 GB file, ~17.1 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (9.21 GB file, ~17.8 GB memory) is a good balance. If more memory is available, Q5_K_M or Q6_K provide higher quality at the cost of larger memory usage.
What GPU do you need for Gemma 4 64E A4B 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: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q3_K_M (7.4 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (14.7 GB file, about 23.3 GB in use).
Which Gemma 4 64E A4B Heretic quant should you choose?
Q4_K_M is the usual starting point for Gemma 4 64E A4B Heretic: it balances file size and quality well. Here it is a 9.2 GB file.
The Q8_0 file is 14.7 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 5.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gemma 4 64E A4B Heretic
How much VRAM does Gemma 4 64E A4B Heretic need?
About 17.8 GB at Q4_K_M with an 8K context window. That is the 9.2 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 Gemma 4 64E A4B Heretic on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma 4 64E A4B Heretic GGUF?
It depends on the quant: Q2_K is 5.9 GB, Q3_K_S is 6.8 GB, Q3_K_M is 7.4 GB, Q3_K_L is 7.7 GB, IQ4_XS is 7.8 GB, Q4_K_S is 8.5 GB and 5 more.
What context length does Gemma 4 64E A4B 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 64E A4B Heretic GGUF?
The files are on Hugging Face in the mradermacher/Gemma-4-64E-A4B-Heretic-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Gemma 4 64E A4B Heretic on 8 GB VRAM?
Use the Q4_K_S quant, which requires about 17.1 GB memory at 8 k context, so 8 GB VRAM is insufficient. A larger VRAM or a lower quant is needed.
Does this model support vision?
No native vision support. Pair with SigLIP mmproj for multimodal capabilities.
What is the recommended sampler setting?
Top‑P 0.9 with Temp 0.7–0.8 and Repeat Penalty 1.15 for best results.