IN

Internlm2_5 20b Chat Abliterated

InternLMGGUF by byroneversonUpdated 2024-09-03
Download on Hugging Face
Parameters19.9B
Context32K
Layers48
Architectureinternlm2
Smallest quant12.0 GB
Quick answer

Internlm2_5 20b Chat Abliterated 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. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Internlm2_5 20b Chat Abliterated is a 19.9B-parameter InternLM model in GGUF format, quantized by byroneverson. Its trained context length is 32K tokens. The repository has 1 quant file, from 12.0 GB (Q4_K_M) to 12.0 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M12.0 GB 14.1 GB
Too big Get file →

What GPU do you need for Internlm2_5 20b Chat Abliterated?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q4_K_M (12.0 GB file, about 14.1 GB in use).

Which Internlm2_5 20b Chat Abliterated quant should you choose?

Q4_K_M is the usual starting point for Internlm2_5 20b Chat Abliterated: it balances file size and quality well. Here it is a 12.0 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureinternlm2
Parameters19.9B
Layers48
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized bybyroneverson
FamilyInternLM
Licenseapache-2.0
Downloads (HF)29
Last updated2024-09-03

Frequently asked questions about Internlm2_5 20b Chat Abliterated

How much VRAM does Internlm2_5 20b Chat Abliterated 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_5 20b Chat Abliterated on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Internlm2_5 20b Chat Abliterated GGUF?

It depends on the quant: Q4_K_M is 12.0 GB.

What context length does Internlm2_5 20b Chat Abliterated support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download Internlm2_5 20b Chat Abliterated GGUF?

The files are on Hugging Face in the byroneverson/internlm2_5-20b-chat-abliterated-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_5 20b Chat Abliterated 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.

Other GGUFs of internlm2_5-20b-chat-abliterated

Similar models

Browse all →

More from byroneverson

All by byroneverson →

More InternLM models

All InternLM →

Other medium models

All medium models →