ME

Merak 7B v4

MerakGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant3.1 GB
Quick answer

Merak 7B v4 needs about 6.4 GB of memory at Q4_K_M (a 4.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 14 quants, from 3.1 GB (Q2_K) to 8.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Merak 7B v4 – Indonesian language LLM based on Mistral‑7B‑OpenOrca

Merak 7B v4 is a 7.24 billion‑parameter language model fine‑tuned on Indonesian Wikipedia. It supports a 32 768‑token context window and is released under CC‑BY‑NC‑SA‑4.0. The model is available in multiple GGUF quantizations.

Good at

  • Fine‑tuned Indonesian text generation
  • ChatML compatible responses
  • Efficient inference with low‑bit quantization

Limits

  • No vision support
  • Requires CUDA driver and Python 3.10+
  • License restricts commercial use

Best for

  • Chatbots in Indonesian
  • Content creation for Indonesian media
  • Research on Indonesian NLP

Who it’s for. Researchers, developers, and AI enthusiasts working with Indonesian language data who need a compact, open‑source LLM. The model is suitable for non‑commercial projects and educational use.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.1 GB 4.7 GB
Fits Get file →
IQ3_XS3.4 GB 5.0 GB
Fits Get file →
Q3_K_S3.6 GB 5.2 GB
Fits Get file →
IQ3_S3.6 GB 5.2 GB
Fits Get file →
IQ3_M3.7 GB 5.3 GB
Fits Get file →
Q3_K_M3.9 GB 5.5 GB
Fits Get file →
Q3_K_L4.2 GB 5.8 GB
Fits Get file →
IQ4_XS4.4 GB 5.9 GB
Fits Get file →
Q4_K_S4.6 GB 6.1 GB
Fits Get file →
Q4_K_M4.8 GB 6.4 GB
Fits Get file →
Q5_K_S5.4 GB 7.0 GB
Fits Get file →
Q5_K_M5.5 GB 7.1 GB
Fits Get file →
Q6_K6.4 GB 7.9 GB
Tight Get file →
Q8_08.1 GB 9.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 4.79 GB, estimated 6.4 GB memory). If you have 10 GB VRAM, Q5_K_M (5.55 GB, 7.1 GB memory) offers higher quality. For 16 GB VRAM, Q6_K (6.36 GB, 7.9 GB memory) or Q8_0 (8.08 GB, 9.7 GB memory) provide the best performance.

What GPU do you need for Merak 7B v4?

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 IQ4_XS (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.4 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.7 GB in use).

Which Merak 7B v4 quant should you choose?

Q4_K_M is the usual starting point for Merak 7B v4: it balances file size and quality well. Here it is a 4.8 GB file.

The Q8_0 file is 8.1 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 Q2_K at 3.1 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
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyMerak
Downloads (HF)1,280
Last updated2024-05-06

Frequently asked questions about Merak 7B v4

How much VRAM does Merak 7B v4 need?

About 6.4 GB at Q4_K_M with an 8K context window. That is the 4.8 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 Merak 7B v4 on an 8 GB GPU?

Yes, with Q6_K: the 6.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Merak 7B v4 GGUF?

It depends on the quant: Q2_K is 3.1 GB, IQ3_XS is 3.4 GB, Q3_K_S is 3.6 GB, IQ3_S is 3.6 GB, IQ3_M is 3.7 GB, Q3_K_M is 3.9 GB and 8 more.

What context length does Merak 7B v4 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 Merak 7B v4 GGUF?

The files are on Hugging Face in the mradermacher/Merak-7B-v4-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 Merak 7B v4 use?

Hugging Face lists the license as cc-by-nc-sa-4.0. 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 Merak 7B v4 on a GPU with 8 GB VRAM?

Yes, use the Q4_K_M quantization which requires approximately 6.4 GB of VRAM at 8 k context.

Does Merak 7B v4 support vision tasks?

No, the model is purely a language model and does not include vision capabilities.

Is the model free for commercial use?

No, the CC‑BY‑NC‑SA‑4.0 license prohibits commercial use without permission.

Other GGUFs of Merak-7B-v4

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Merak models

All Merak →

Other small models

All small models →