BI

Bifrost

BifrostGGUF by mradermacherUpdated 2025-03-08
Download on Hugging Face
Parameters14.7B
Context16K
Layers40
Architecturellama
Smallest quant3.4 GB
Quick answer

Bifrost needs about 11.1 GB of memory at Q4_K_M (a 8.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 3.4 GB (IQ1_S) to 12.0 GB (Q6_K).

14.7B Llama‑based code generation model

Bifrost is a 14.7B parameter Llama model fine‑tuned for secure code generation. It supports up to 16384 context tokens and is released under the Apache‑2.0 license. The model is optimized for enterprise‑grade coding tasks.

Good at

  • Secure code generation
  • Enterprise‑grade compliance
  • Context‑aware programming support

Limits

  • No vision support
  • Requires human supervision for code correctness
  • Large VRAM needed for higher‑quality quants

Best for

  • Automating routine coding tasks
  • Generating secure code snippets
  • Assisting in regulated development environments

Who it’s for. Developers and organizations needing secure, high‑quality code generation in regulated settings. The model is suitable for teams that require compliance with standards such as GDPR, HIPAA, and SOC 2.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S3.4 GB 5.6 GB
Fits Get file →
IQ1_M3.7 GB 5.9 GB
Fits Get file →
IQ2_XXS4.2 GB 6.3 GB
Fits Get file →
IQ2_XS4.6 GB 6.7 GB
Fits Get file →
IQ2_S4.8 GB 7.0 GB
Fits Get file →
IQ2_M5.2 GB 7.4 GB
Tight Get file →
Q2_K_S5.2 GB 7.4 GB
Tight Get file →
Q2_K5.6 GB 7.8 GB
Tight Get file →
IQ3_XXS5.8 GB 8.0 GB
Tight Get file →
IQ3_XS6.2 GB 8.4 GB
Too big Get file →
Q3_K_S6.5 GB 8.7 GB
Too big Get file →
IQ3_S6.5 GB 8.7 GB
Too big Get file →
IQ3_M6.7 GB 8.9 GB
Too big Get file →
Q3_K_M7.2 GB 9.4 GB
Too big Get file →
Q3_K_L7.8 GB 10.0 GB
Too big Get file →
IQ4_XS8.0 GB 10.2 GB
Too big Get file →
Q4_08.4 GB 10.6 GB
Too big Get file →
IQ4_NL8.4 GB 10.6 GB
Too big Get file →
Q4_K_S8.4 GB 10.6 GB
Too big Get file →
Q4_K_M8.9 GB 11.1 GB
Too big Get file →
Q4_19.3 GB 11.4 GB
Too big Get file →
Q5_K_S10.2 GB 12.3 GB
Too big Get file →
Q5_K_M10.4 GB 12.6 GB
Too big Get file →
Q6_K12.0 GB 14.2 GB
Too big Get file →

For 8 GB VRAM use IQ1_S or IQ1_M (est. 5.6–5.9 GB). With 12 GB VRAM IQ2_S or Q2_K are suitable (est. 7–7.8 GB). For 16 GB VRAM Q3_K_M or Q4_K_M can be used (est. 9.4–11.1 GB). Estimates are approximate.

What GPU do you need for Bifrost?

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 IQ1_M (3.7 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_XXS (5.8 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_1 (9.3 GB file, about 11.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (12.0 GB file, about 14.2 GB in use).

Which Bifrost quant should you choose?

Q4_K_M is the usual starting point for Bifrost: it balances file size and quality well. Here it is a 8.9 GB file.

If memory is tight, the smallest file is IQ1_S at 3.4 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

Architecturellama
Parameters14.7B
Layers40
Trained context16,384 tokens
KV cache (fp16)200 KB per token

Source

Quantized bymradermacher
FamilyBifrost
Licenseapache-2.0
Downloads (HF)516
Last updated2025-03-08

Frequently asked questions about Bifrost

How much VRAM does Bifrost need?

About 11.1 GB at Q4_K_M with an 8K context window. That is the 8.9 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 on an 8 GB GPU?

Yes, with IQ3_XXS: the 5.8 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Bifrost GGUF?

It depends on the quant: IQ1_S is 3.4 GB, IQ1_M is 3.7 GB, IQ2_XXS is 4.2 GB, IQ2_XS is 4.6 GB, IQ2_S is 4.8 GB, IQ2_M is 5.2 GB and 18 more.

What context length does Bifrost support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.7 GB at 8K and 3.4 GB at 16K.

Where can I download Bifrost GGUF?

The files are on Hugging Face in the mradermacher/Bifrost-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 Bifrost 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 Bifrost on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quant, which estimate 5.6–5.9 GB memory at 8k context.

Does Bifrost support image input?

No, the model has no vision capabilities.

What license applies to Bifrost?

The model is released under the Apache‑2.0 license.

Other GGUFs of Bifrost

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Bifrost models

All Bifrost →

Other medium models

All medium models →