Heimdallr 26b A4B v0.35 needs about 22.8 GB of memory at MXFP4 (a 14.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Heimdallr 26b A4B v0.35 is a 25.2B-parameter Heimdallr model in GGUF format, quantized by Phil2Sat. Its trained context length is 256K tokens. The repository has 1 quant file, from 14.2 GB (MXFP4) to 14.2 GB (MXFP4).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4 | 14.2 GB | 22.8 GB | Too big | Get file → |
What GPU do you need for Heimdallr 26b A4B v0.35?
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: the best quant that fits is MXFP4 (14.2 GB file, about 22.8 GB in use).
Which Heimdallr 26b A4B v0.35 quant should you choose?
MXFP4 (14.2 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Heimdallr 26b A4B v0.35
How much VRAM does Heimdallr 26b A4B v0.35 need?
About 22.8 GB at MXFP4 with an 8K context window. That is the 14.2 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 Heimdallr 26b A4B v0.35 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 22.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Heimdallr 26b A4B v0.35 GGUF?
It depends on the quant: MXFP4 is 14.2 GB.
What context length does Heimdallr 26b A4B v0.35 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 v0.35 GGUF?
The files are on Hugging Face in the Phil2Sat/Heimdallr-26B-A4B-v0.35-I-Compact-MXFP4-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.