GA

ganjar 4

GanjarGGUF by KernelUpdated 2023-12-25
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant7.7 GB
Quick answer

ganjar 4 needs about 9.3 GB of memory at its main file (a 7.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 7.7 GB to 49.6 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Ganjar 4 – a 7.24‑billion‑parameter llama model

Ganjar 4 is a 7.24‑billion‑parameter llama architecture model. It was trained on 32,768 context tokens. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • High‑parameter density
  • Versatile language tasks

Limits

  • No license information provided
  • No vision support
  • Requires high VRAM for full precision

Best for

  • Research on large‑context LLMs
  • Fine‑tuning for specialized domains
  • Benchmarking llama models

Who it’s for. Researchers and developers who need a large‑parameter llama model with extended context. The model is suitable for those who can allocate sufficient GPU memory and are comfortable with GGUF quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—7.7 GB 9.3 GB
Too big Get file →
—7.7 GB 9.3 GB
Too big Get file →
—7.7 GB 9.3 GB
Too big Get file →
—32.2 GB 33.8 GB
Too big Get file →
—49.6 GB 51.2 GB
Too big Get file →

For 8‑k context, the 7.7 GB GGUF file needs about 9.3 GB of VRAM. If you have 12 GB VRAM, use the 7.7 GB file. For larger VRAM (24 GB+), the 32.23 GB file uses about 33.8 GB of VRAM, and the 49.62 GB file uses about 51.2 GB of VRAM.

What GPU do you need for ganjar 4?

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: the best quant that fits is the main file (7.7 GB file, about 9.3 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (7.7 GB file, about 9.3 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (7.7 GB file, about 9.3 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (7.7 GB file, about 9.3 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (32.2 GB file, about 33.8 GB in use).

Which ganjar 4 quant should you choose?

If memory is tight, the smallest file is the first one in the table at 7.7 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byKernel
FamilyGanjar
RepositoryKernel/ganjar_4
Downloads (HF)694
Last updated2023-12-25

Frequently asked questions about ganjar 4

How much VRAM does ganjar 4 need?

About 9.3 GB at its main file with an 8K context window. That is the 7.7 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 ganjar 4 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ganjar 4 GGUF?

It depends on the quant: file is 7.7 GB, file is 7.7 GB, file is 7.7 GB, file is 32.2 GB, file is 49.6 GB.

What context length does ganjar 4 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download ganjar 4 GGUF?

The files are on Hugging Face in the Kernel/ganjar_4 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Ganjar 4 on 8 GB VRAM?

No, the smallest GGUF file requires about 9.3 GB of VRAM at 8‑k context, which exceeds 8 GB.

What is the context length of Ganjar 4?

The model was trained on 32,768 context tokens.

Does Ganjar 4 support vision tasks?

No, the model does not have vision capabilities.

Similar models

Browse all →

Other small models

All small models →