LL

internlm2 math 20b llama

LlamaGGUF by LoneStrikerUpdated 2024-01-25
Download on Hugging Face
Parameters19.9B
Context8K
Layers48
Architecturellama
Smallest quant8.8 GB
Quick answer

internlm2 math 20b llama needs about 14.1 GB of memory at Q4_K_M (a 12.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 9 quants, from 8.8 GB (Q3_K_S) to 21.1 GB (Q8_0).

internlm2 math 20b llama is a 19.9B-parameter Llama model in GGUF format, quantized by LoneStriker. Its trained context length is 8K tokens. The repository has 9 quant files, from 8.8 GB (Q3_K_S) to 21.1 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S8.8 GB 10.9 GB
Too big Get file →
Q3_K_M9.7 GB 11.8 GB
Too big Get file →
Q3_K_L10.6 GB 12.7 GB
Too big Get file →
Q4_K_S11.4 GB 13.5 GB
Too big Get file →
Q4_K_M12.0 GB 14.1 GB
Too big Get file →
Q5_K_S13.7 GB 15.8 GB
Too big Get file →
Q5_K_M14.1 GB 16.2 GB
Too big Get file →
Q6_K16.3 GB 18.4 GB
Too big Get file →
Q8_021.1 GB 23.2 GB
Too big Get file →

What GPU do you need for internlm2 math 20b llama?

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 Q3_K_M (9.7 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_S (13.7 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (21.1 GB file, about 23.2 GB in use).

Which internlm2 math 20b llama quant should you choose?

Q4_K_M is the usual starting point for internlm2 math 20b llama: it balances file size and quality well. Here it is a 12.0 GB file.

The Q8_0 file is 21.1 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 Q3_K_S at 8.8 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
Parameters19.9B
Layers48
Trained context8,192 tokens
KV cache (fp16)192 KB per token

Source

Quantized byLoneStriker
FamilyLlama
Licenseother
Downloads (HF)478
Last updated2024-01-25

Frequently asked questions about internlm2 math 20b llama

How much VRAM does internlm2 math 20b llama need?

About 14.1 GB at Q4_K_M with an 8K context window. That is the 12.0 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 internlm2 math 20b llama on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of internlm2 math 20b llama GGUF?

It depends on the quant: Q3_K_S is 8.8 GB, Q3_K_M is 9.7 GB, Q3_K_L is 10.6 GB, Q4_K_S is 11.4 GB, Q4_K_M is 12.0 GB, Q5_K_S is 13.7 GB and 3 more.

What context length does internlm2 math 20b llama support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.6 GB at 8K and 1.6 GB at 8K.

Where can I download internlm2 math 20b llama GGUF?

The files are on Hugging Face in the LoneStriker/internlm2-math-20b-llama-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 internlm2 math 20b llama use?

Hugging Face lists the license as other. 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 LoneStriker

All by LoneStriker →

More Llama models

All Llama →

Other medium models

All medium models →