Heimdallr 26B A4B Final needs about 25.3 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 16.8 GB (Q4_K_M) to 22.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Heimdallr 26B A4B Final – a 25.2B parameter gemma4 model
Heimdallr 26B A4B Final is a 25.2B parameter gemma4 model with 4B active parameters in a mixture of experts. It was trained on 262144 context tokens and is licensed under apache-2.0.
Good at
- reasoning
- roleplay
- tools
Limits
- trained context 262144 tokens
- no vision support
- requires large VRAM
Best for
- complex reasoning tasks
- interactive roleplay
- tool‑using applications
Who it’s for. Developers and researchers needing a large, multi‑expert gemma4 model for advanced text generation. The model is suitable for applications that can accommodate its high memory footprint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 16.8 GB | 25.3 GB | Too big | Get file → | |
| Q5_K_M | 19.1 GB | 27.7 GB | Too big | Get file → | |
| Q6_K | 22.6 GB | 31.2 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (file size 16.8 GB, estimated 25.3 GB memory at 8 k context). For 12 GB VRAM use Q5_K_M (19.13 GB, 27.7 GB memory). For 16 GB VRAM use Q6_K (22.64 GB, 31.2 GB memory). Estimates are approximate.
What GPU do you need for Heimdallr 26B A4B Final?
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: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q6_K (22.6 GB file, about 31.2 GB in use).
Which Heimdallr 26B A4B Final quant should you choose?
Q4_K_M is the usual starting point for Heimdallr 26B A4B Final: it balances file size and quality well. Here it is a 16.8 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Heimdallr 26B A4B Final
How much VRAM does Heimdallr 26B A4B Final need?
About 25.3 GB at Q4_K_M with an 8K context window. That is the 16.8 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 Heimdallr 26B A4B Final on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 25.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Heimdallr 26B A4B Final GGUF?
It depends on the quant: Q4_K_M is 16.8 GB, Q5_K_M is 19.1 GB, Q6_K is 22.6 GB.
What context length does Heimdallr 26B A4B Final 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 Heimdallr 26B A4B Final GGUF?
The files are on Hugging Face in the ReadyArt/Heimdallr-26B-A4B-Final-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 Heimdallr 26B A4B Final 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 Heimdallr 26B A4B Final on 8 GB VRAM?
Use the Q4_K_M quantized file; it requires about 25.3 GB memory at 8 k context, so 8 GB VRAM is insufficient.
Does the model support vision?
No, the model has no vision capability.
What license does the model use?
The model is released under the apache-2.0 license.