JA

Janus Pro 7B LM

JanusGGUF by mradermacherUpdated 2025-01-30
Download on Hugging Face
Parameters6.91B
Context16K
Layers30
Architecturellama
Smallest quant1.7 GB
Quick answer

Janus Pro 7B LM needs about 8.7 GB of memory at Q4_K_M (a 4.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 1.7 GB (IQ1_S) to 5.7 GB (Q6_K).

Janus Pro 7B LM – 6.91B parameter LLaMA‑based language model

Janus Pro 7B LM is a 6.91B parameter LLaMA architecture model. It supports a context length of 16384 tokens and is released under the MIT license. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • LLM‑only architecture
  • MIT licensed

Limits

  • No vision support
  • No mixture of experts
  • Context limited to 16384 tokens

Best for

  • Chat applications
  • Text generation
  • Fine‑tuning on custom data

Who it’s for. Developers and researchers who need a lightweight, open‑source LLaMA model for text‑only tasks. The model is suitable for local deployment with GGUF support.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.7 GB 6.3 GB
Fits Get file →
IQ1_M1.8 GB 6.4 GB
Fits Get file →
IQ2_XXS2.0 GB 6.6 GB
Fits Get file →
IQ2_XS2.2 GB 6.7 GB
Fits Get file →
IQ2_S2.4 GB 6.9 GB
Fits Get file →
Q2_K_S2.5 GB 7.0 GB
Fits Get file →
IQ2_M2.5 GB 7.1 GB
Fits Get file →
Q2_K2.7 GB 7.2 GB
Tight Get file →
IQ3_XXS2.8 GB 7.3 GB
Tight Get file →
IQ3_XS3.0 GB 7.5 GB
Tight Get file →
IQ3_S3.1 GB 7.7 GB
Tight Get file →
Q3_K_S3.1 GB 7.7 GB
Tight Get file →
IQ3_M3.3 GB 7.8 GB
Tight Get file →
Q3_K_M3.5 GB 8.0 GB
Tight Get file →
Q3_K_L3.7 GB 8.3 GB
Too big Get file →
IQ4_XS3.8 GB 8.3 GB
Too big Get file →
IQ4_NL4.0 GB 8.5 GB
Too big Get file →
Q4_04.0 GB 8.5 GB
Too big Get file →
Q4_K_S4.0 GB 8.6 GB
Too big Get file →
Q4_K_M4.2 GB 8.7 GB
Too big Get file →
Q4_14.4 GB 8.9 GB
Too big Get file →
Q5_K_S4.8 GB 9.3 GB
Too big Get file →
Q5_K_M4.9 GB 9.5 GB
Too big Get file →
Q6_K5.7 GB 10.2 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (1.73 GB file, 6.3 GB memory) or IQ1_M (1.85 GB file, 6.4 GB memory). For 12 GB VRAM, Q4_K_M (4.22 GB file, 8.7 GB memory) or Q5_K_M (4.93 GB file, 9.5 GB memory) are recommended. Larger VRAM allows higher‑quality quants such as Q6_K.

What GPU do you need for Janus Pro 7B LM?

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: the best quant that fits is Q3_K_M (3.5 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (5.7 GB file, about 10.2 GB in use).

Which Janus Pro 7B LM quant should you choose?

Q4_K_M is the usual starting point for Janus Pro 7B LM: it balances file size and quality well. Here it is a 4.2 GB file.

If memory is tight, the smallest file is IQ1_S at 1.7 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
Parameters6.91B
Layers30
Trained context16,384 tokens
KV cache (fp16)480 KB per token

Source

Quantized bymradermacher
FamilyJanus
Licensemit
Downloads (HF)685
Last updated2025-01-30

Frequently asked questions about Janus Pro 7B LM

How much VRAM does Janus Pro 7B LM need?

About 8.7 GB at Q4_K_M with an 8K context window. That is the 4.2 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 Janus Pro 7B LM on an 8 GB GPU?

Yes, with Q3_K_M: the 3.5 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 Janus Pro 7B LM GGUF?

It depends on the quant: IQ1_S is 1.7 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.0 GB, IQ2_XS is 2.2 GB, IQ2_S is 2.4 GB, Q2_K_S is 2.5 GB and 18 more.

What context length does Janus Pro 7B LM support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 4.0 GB at 8K and 8.1 GB at 16K.

Where can I download Janus Pro 7B LM GGUF?

The files are on Hugging Face in the mradermacher/Janus-Pro-7B-LM-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 Janus Pro 7B LM use?

Hugging Face lists the license as mit. 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 this model on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations, which require about 6.3–6.4 GB of VRAM at 8k context.

Does the model support vision tasks?

No, Janus Pro 7B LM is a language‑model only and does not include vision capabilities.

What license does the model use?

The model is released under the MIT license, allowing free use and modification.

Other GGUFs of Janus-Pro-7B-LM

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Janus models

All Janus →

Other small models

All small models →