NE

NeuralStar_FusionWriter_4x7b

NeuralstarGGUF by mradermacherUpdated 2024-06-08
Download on Hugging Face
Parameters24.2B
Context32K
Layers32
Architecturellama
Smallest quant8.8 GB
Quick answer

NeuralStar_FusionWriter_4x7b needs about 16.2 GB of memory at Q4_K_M (a 14.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 14 quants, from 8.8 GB (Q2_K) to 25.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

24.2B parameter MoE LLaMA model with 32k context

NeuralStar_FusionWriter_4x7b is a 24.2B parameter mixture of experts LLaMA model. It supports a 32768 token context window and is released under the Apache‑2.0 license.

Good at

  • Large‑context generation
  • Multi‑expert reasoning
  • High‑capacity text modeling

Limits

  • Requires up to 27.2GB VRAM for Q8_0 at 8k context
  • Large model size limits use on low‑memory systems
  • Mixture of experts may need special handling

Best for

  • Long‑form content creation
  • Complex reasoning tasks
  • Research prototyping

Who it’s for. Developers and researchers who need a large LLaMA‑based MoE model. It runs with llama.cpp and GGUF quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K8.8 GB 10.4 GB
Too big Get file →
IQ3_XS9.9 GB 11.5 GB
Too big Get file →
Q3_K_S10.4 GB 12.0 GB
Too big Get file →
IQ3_S10.5 GB 12.0 GB
Too big Get file →
IQ3_M10.6 GB 12.2 GB
Too big Get file →
Q3_K_M11.6 GB 13.2 GB
Too big Get file →
Q3_K_L12.5 GB 14.1 GB
Too big Get file →
IQ4_XS13.0 GB 14.6 GB
Too big Get file →
Q4_K_S13.7 GB 15.3 GB
Too big Get file →
Q4_K_M14.6 GB 16.2 GB
Too big Get file →
Q5_K_S16.6 GB 18.2 GB
Too big Get file →
Q5_K_M17.1 GB 18.7 GB
Too big Get file →
Q6_K19.8 GB 21.4 GB
Too big Get file →
Q8_025.7 GB 27.2 GB
Too big Get file →

For 12GB VRAM, use Q3_K_S (est. 12GB memory). For 16GB VRAM, use Q4_K_M (est. 16.2GB memory). For 20GB VRAM, use Q5_K_M (est. 18.7GB memory).

What GPU do you need for NeuralStar_FusionWriter_4x7b?

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 IQ3_S (10.5 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (13.7 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (19.8 GB file, about 21.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (25.7 GB file, about 27.2 GB in use).

Which NeuralStar_FusionWriter_4x7b quant should you choose?

Q4_K_M is the usual starting point for NeuralStar_FusionWriter_4x7b: it balances file size and quality well. Here it is a 14.6 GB file.

The Q8_0 file is 25.7 GB, about 1.8 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 8.8 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
Parameters24.2B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)1,438
Last updated2024-06-08

Frequently asked questions about NeuralStar_FusionWriter_4x7b

How much VRAM does NeuralStar_FusionWriter_4x7b need?

About 16.2 GB at Q4_K_M with an 8K context window. That is the 14.6 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 NeuralStar_FusionWriter_4x7b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of NeuralStar_FusionWriter_4x7b GGUF?

It depends on the quant: Q2_K is 8.8 GB, IQ3_XS is 9.9 GB, Q3_K_S is 10.4 GB, IQ3_S is 10.5 GB, IQ3_M is 10.6 GB, Q3_K_M is 11.6 GB and 8 more.

What context length does NeuralStar_FusionWriter_4x7b 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 NeuralStar_FusionWriter_4x7b GGUF?

The files are on Hugging Face in the mradermacher/NeuralStar_FusionWriter_4x7b-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 NeuralStar_FusionWriter_4x7b 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 this model on 8GB VRAM?

No, the smallest quant requires 10.4GB memory at 8k context.

Is the model licensed for commercial use?

Yes, under Apache‑2.0 with attribution.

Does it support vision?

No vision capabilities are provided.

Other GGUFs of NeuralStar_FusionWriter_4x7b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Neuralstar models

All Neuralstar →

Other medium models

All medium models →