CA

calm2-7b

CalmGGUF by mmngaUpdated 2023-11-03
Download on Hugging Face
Parameters7.01B
Context4K
Layers32
Architecturellama
Smallest quant3.0 GB
Quick answer

calm2-7b needs about 9.1 GB of memory at Q4_K_M (a 4.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 3.0 GB (Q2_K) to 7.5 GB (Q8_0).

calm2-7b is a 7.01B-parameter Calm model in GGUF format, quantized by mmnga. Its trained context length is 4K tokens. The repository has 12 quant files, from 3.0 GB (Q2_K) to 7.5 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.0 GB 5.6 GB
Fits Get file →
Q3_K_S3.1 GB 5.8 GB
Fits Get file →
Q3_K_M3.5 GB 6.1 GB
Fits Get file →
Q3_K_L3.8 GB 6.4 GB
Fits Get file →
Q4_04.0 GB 6.7 GB
Fits Get file →
Q4_K_S4.0 GB 6.7 GB
Fits Get file →
Q4_K_M4.3 GB 6.9 GB
Fits Get file →
Q5_04.9 GB 7.5 GB
Tight Get file →
Q5_K_S4.9 GB 7.5 GB
Tight Get file →
Q5_K_M5.0 GB 7.6 GB
Tight Get file →
Q6_K5.8 GB 8.4 GB
Too big Get file →
Q8_07.5 GB 10.1 GB
Too big Get file →

What GPU do you need for calm2-7b?

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_S (3.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (5.8 GB file, about 10.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.5 GB file, about 12.2 GB in use).

Which calm2-7b quant should you choose?

Q4_K_M is the usual starting point for calm2-7b: it balances file size and quality well. Here it is a 4.3 GB file.

The Q8_0 file is 7.5 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 3.0 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
Parameters7.01B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymmnga
FamilyCalm
Licenseapache-2.0
Downloads (HF)283
Last updated2023-11-03

Frequently asked questions about calm2-7b

How much VRAM does calm2-7b need?

About 9.1 GB at Q4_K_M with an 8K context window. That is the 4.3 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 calm2-7b on an 8 GB GPU?

Yes, with Q3_K_S: the 3.1 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 calm2-7b GGUF?

It depends on the quant: Q2_K is 3.0 GB, Q3_K_S is 3.1 GB, Q3_K_M is 3.5 GB, Q3_K_L is 3.8 GB, Q4_0 is 4.0 GB, Q4_K_S is 4.0 GB and 6 more.

What context length does calm2-7b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download calm2-7b GGUF?

The files are on Hugging Face in the mmnga/cyberagent-calm2-7b-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 calm2-7b 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.

Similar models

Browse all →

More from mmnga

All by mmnga →

More Calm models

All Calm →

Other small models

All small models →