RE

ReWiz Nemo 12B Instruct

RewizGGUF by theprintUpdated 2024-11-03
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant5.5 GB
Quick answer

ReWiz Nemo 12B Instruct needs about 9.3 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 8 quants, from 5.5 GB (Q3_K_S) to 24.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

ReWiz Nemo 12B Instruct – a 12.2B parameter instruction model

ReWiz Nemo 12B Instruct is a 12.2B parameter llama‑based model fine‑tuned for instruction following. It was trained on reasoning and de‑censoring data sets and released under the apache‑2.0 license.

Good at

  • Instruction following
  • Reasoning tasks
  • De‑censoring content

Limits

  • No vision support
  • Requires large VRAM for higher quantizations
  • No explicit language support list

Best for

  • Chatbot development
  • Content moderation tools
  • Educational tutoring

Who it’s for. Developers building instruction‑driven applications who need a model with a balance of size and performance. The model is suitable for users with access to GPU resources that can handle 8k context length.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S5.5 GB 7.4 GB
Tight Get file →
Q3_K_M6.1 GB 7.9 GB
Tight Get file →
Q4_K_S7.1 GB 9.0 GB
Too big Get file →
Q4_K_M7.5 GB 9.3 GB
Too big Get file →
Q5_K_M8.7 GB 10.6 GB
Too big Get file →
Q6_K10.1 GB 11.9 GB
Too big Get file →
Q8_013.0 GB 14.9 GB
Too big Get file →
F1624.5 GB 26.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 7.12 GB, estimated memory 9 GB). If 12 GB VRAM is available, Q4_K_M (7.48 GB, 9.3 GB) or Q5_K_M (8.73 GB, 10.6 GB) are viable. Higher precision quants such as Q8_0 or F16 require more than 14 GB VRAM.

What GPU do you need for ReWiz Nemo 12B Instruct?

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 (6.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (10.1 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
  • 32 GB VRAM: the best quant that fits is F16 (24.5 GB file, about 26.3 GB in use).

Which ReWiz Nemo 12B Instruct quant should you choose?

Q4_K_M is the usual starting point for ReWiz Nemo 12B Instruct: it balances file size and quality well. Here it is a 7.5 GB file.

The Q8_0 file is 13.0 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 Q3_K_S at 5.5 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters12.2B
Layers40
Trained context1,024,000 tokens
KV cache (fp16)160 KB per token

Source

Quantized bytheprint
FamilyRewiz
Licenseapache-2.0
Downloads (HF)1,075
Last updated2024-11-03

Frequently asked questions about ReWiz Nemo 12B Instruct

How much VRAM does ReWiz Nemo 12B Instruct need?

About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.5 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 ReWiz Nemo 12B Instruct on an 8 GB GPU?

Yes, with Q3_K_M: the 6.1 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 ReWiz Nemo 12B Instruct GGUF?

It depends on the quant: Q3_K_S is 5.5 GB, Q3_K_M is 6.1 GB, Q4_K_S is 7.1 GB, Q4_K_M is 7.5 GB, Q5_K_M is 8.7 GB, Q6_K is 10.1 GB and 2 more.

What context length does ReWiz Nemo 12B Instruct support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download ReWiz Nemo 12B Instruct GGUF?

The files are on Hugging Face in the theprint/ReWiz-Nemo-12B-Instruct-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 ReWiz Nemo 12B Instruct 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 ReWiz Nemo 12B Instruct on 8 GB VRAM?

Yes, the Q4_K_S quantization uses about 9 GB of VRAM at 8k context, which fits within an 8 GB GPU with some overhead.

What license does this model use?

The model is released under the apache-2.0 license.

Is this model suitable for vision tasks?

No, the model does not support vision capabilities.

Other GGUFs of ReWiz-Nemo-12B-Instruct

Similar models

Browse all →

More from theprint

All by theprint →

More Rewiz models

All Rewiz →

Other medium models

All medium models →