NE

Nemo Base Pruned Proj

NemoGGUF by mradermacherUpdated 2025-09-06
Download on Hugging Face
Parameters6.59B
Context128K
Layers40
Architecturellama
Smallest quant2.7 GB
Quick answer

Nemo Base Pruned Proj needs about 5.9 GB of memory at Q4_K_M (a 4.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 2.7 GB (Q2_K) to 13.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Nemo Base Pruned Proj is a 6.59B-parameter Nemo model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 12 quant files, from 2.7 GB (Q2_K) to 13.2 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.7 GB 4.6 GB
Fits Get file →
Q3_K_S3.1 GB 4.9 GB
Fits Get file →
Q3_K_M3.4 GB 5.2 GB
Fits Get file →
Q3_K_L3.6 GB 5.5 GB
Fits Get file →
IQ4_XS3.8 GB 5.6 GB
Fits Get file →
Q4_K_S3.9 GB 5.7 GB
Fits Get file →
Q4_K_M4.0 GB 5.9 GB
Fits Get file →
Q5_K_S4.6 GB 6.5 GB
Fits Get file →
Q5_K_M4.7 GB 6.6 GB
Fits Get file →
Q6_K5.4 GB 7.3 GB
Tight Get file →
Q8_07.0 GB 8.8 GB
Too big Get file →
F1613.2 GB 15.0 GB
Too big Get file →

What GPU do you need for Nemo Base Pruned Proj?

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 Q4_K_M (4.0 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.4 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.0 GB file, about 8.8 GB in use).
  • 16 GB VRAM: the best quant that fits is F16 (13.2 GB file, about 15.0 GB in use).

Which Nemo Base Pruned Proj quant should you choose?

Q4_K_M is the usual starting point for Nemo Base Pruned Proj: it balances file size and quality well. Here it is a 4.0 GB file.

The Q8_0 file is 7.0 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 Q2_K at 2.7 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
Parameters6.59B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized bymradermacher
FamilyNemo
Downloads (HF)52
Last updated2025-09-06

Frequently asked questions about Nemo Base Pruned Proj

How much VRAM does Nemo Base Pruned Proj need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.0 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 Nemo Base Pruned Proj on an 8 GB GPU?

Yes, with Q6_K: the 5.4 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Nemo Base Pruned Proj GGUF?

It depends on the quant: Q2_K is 2.7 GB, Q3_K_S is 3.1 GB, Q3_K_M is 3.4 GB, Q3_K_L is 3.6 GB, IQ4_XS is 3.8 GB, Q4_K_S is 3.9 GB and 6 more.

What context length does Nemo Base Pruned Proj support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 Nemo Base Pruned Proj GGUF?

The files are on Hugging Face in the mradermacher/Nemo-Base-Pruned-Proj-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Nemo models

All Nemo →

Other small models

All small models →