BI

Bifrost-27B-GGUF

BifrostGGUF by JoumdaneUpdated 2025-04-04
Download on Hugging Face
Parameters27B
Context128K
Layers62
Architecturegemma3
Smallest quant1.0 GB
Quick answer

Bifrost-27B-GGUF needs about 21.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 19 quants, from 1.0 GB (IQ3_XXS) to 28.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.

Bifrost-27B-GGUF – enterprise‑grade code generation model

Bifrost-27B-GGUF is a 27‑billion‑parameter model based on gemma3 architecture. It is fine‑tuned for secure and efficient code generation in regulated environments. The model supports up to 131072 context tokens.

Good at

  • Secure code generation
  • Enterprise‑level compliance
  • High‑quality programming assistance

Limits

  • Requires human supervision for code correctness
  • No vision support
  • Large memory footprint for higher‑quality quants

Best for

  • Automating routine coding tasks
  • Generating secure code snippets
  • Assisting in compliance‑aware development

Who it’s for. Developers and organizations needing reliable, secure code generation. The model is suitable for teams that prioritize safety, compliance, and efficiency in software development workflows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XXS1.0 GB 5.6 GB
Fits Get file →
Q2_K10.5 GB 15.2 GB
Too big Get file →
IQ3_XS11.6 GB 16.2 GB
Too big Get file →
IQ3_S12.2 GB 16.8 GB
Too big Get file →
Q3_K_S12.2 GB 16.8 GB
Too big Get file →
IQ3_M12.5 GB 17.2 GB
Too big Get file →
Q3_K13.4 GB 18.1 GB
Too big Get file →
Q3_K_M13.4 GB 18.1 GB
Too big Get file →
Q3_K_L14.5 GB 19.2 GB
Too big Get file →
IQ4_XS14.9 GB 19.6 GB
Too big Get file →
IQ4_NL15.7 GB 20.3 GB
Too big Get file →
Q4_K_S15.7 GB 20.3 GB
Too big Get file →
Q4_K16.5 GB 21.2 GB
Too big Get file →
Q4_K_M16.5 GB 21.2 GB
Too big Get file →
Q5_K_S18.8 GB 23.4 GB
Too big Get file →
Q5_K19.3 GB 23.9 GB
Too big Get file →
Q5_K_M19.3 GB 23.9 GB
Too big Get file →
Q6_K22.2 GB 26.8 GB
Too big Get file →
Q8_028.7 GB 33.4 GB
Too big Get file →

For 8‑GB VRAM, use Q2_K (10.5 GB file, 15.2 GB memory at 8k context). For 16‑GB VRAM, Q4_K_M (16.55 GB file, 21.2 GB memory). For 32‑GB VRAM, Q6_K (22.17 GB file, 26.8 GB memory).

What GPU do you need for Bifrost-27B-GGUF?

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: the best quant that fits is IQ3_XXS (1.0 GB file, about 5.6 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_XXS (1.0 GB file, about 5.6 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ3_XXS (1.0 GB file, about 5.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q2_K (10.5 GB file, about 15.2 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K (19.3 GB file, about 23.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.2 GB file, about 26.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (28.7 GB file, about 33.4 GB in use).

Which Bifrost-27B-GGUF quant should you choose?

Q4_K_M is the usual starting point for Bifrost-27B-GGUF: it balances file size and quality well. Here it is a 16.5 GB file.

The Q8_0 file is 28.7 GB, about 1.7 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 IQ3_XXS at 1.0 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters27B
Layers62
Trained context131,072 tokens
KV cache (fp16)496 KB per token

Source

Quantized byJoumdane
FamilyBifrost
Licensegemma
Downloads (HF)657
Last updated2025-04-04

Frequently asked questions about Bifrost-27B-GGUF

How much VRAM does Bifrost-27B-GGUF need?

About 21.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 Bifrost-27B-GGUF on an 8 GB GPU?

Yes, with IQ3_XXS: the 1.0 GB file needs about 5.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Bifrost-27B-GGUF GGUF?

It depends on the quant: IQ3_XXS is 1.0 GB, Q2_K is 10.5 GB, IQ3_XS is 11.6 GB, IQ3_S is 12.2 GB, Q3_K_S is 12.2 GB, IQ3_M is 12.5 GB and 13 more.

What context length does Bifrost-27B-GGUF support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.6 GB at 32K.

Where can I download Bifrost-27B-GGUF GGUF?

The files are on Hugging Face in the Joumdane/Bifrost-27B-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 Bifrost-27B-GGUF 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 Bifrost-27B-GGUF on 8 GB VRAM?

Yes, the Q2_K quant uses 15.2 GB memory at 8k context, which fits within 8 GB VRAM when using efficient batching.

Does the model support image input?

No, Bifrost-27B-GGUF does not include vision capabilities.

What license applies to this model?

The model is licensed under the gemma license, as indicated in the parent model card.

Similar models

Browse all →

More from Joumdane

All by Joumdane →

More Bifrost models

All Bifrost →

Other medium models

All medium models →