IN

InternLM2

InternLMGGUF by RichardErkhovUpdated 2024-05-09
Download on Hugging Face
Parameters1.89B
Context32K
Layers24
Architectureinternlm2
Smallest quant0.8 GB
Quick answer

InternLM2 needs about 2.5 GB of memory at Q4_K_M (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 21 quants, from 0.8 GB (Q2_K) to 1.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

InternLM2 is a 1.89B-parameter InternLM model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 21 quant files, from 0.8 GB (Q2_K) to 1.6 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.8 GB 2.1 GB
Fits Get file →
IQ3_XS0.9 GB 2.2 GB
Fits Get file →
IQ3_S0.9 GB 2.2 GB
Fits Get file →
Q3_K_S0.9 GB 2.2 GB
Fits Get file →
IQ3_M0.9 GB 2.2 GB
Fits Get file →
Q3_K1.0 GB 2.3 GB
Fits Get file →
Q3_K_M1.0 GB 2.3 GB
Fits Get file →
Q3_K_L1.0 GB 2.3 GB
Fits Get file →
IQ4_XS1.1 GB 2.4 GB
Fits Get file →
Q4_01.1 GB 2.4 GB
Fits Get file →
IQ4_NL1.1 GB 2.4 GB
Fits Get file →
Q4_K_S1.1 GB 2.4 GB
Fits Get file →
Q4_K1.2 GB 2.5 GB
Fits Get file →
Q4_K_M1.2 GB 2.5 GB
Fits Get file →
Q4_11.2 GB 2.5 GB
Fits Get file →
Q5_01.3 GB 2.6 GB
Fits Get file →
Q5_K_S1.3 GB 2.6 GB
Fits Get file →
Q5_K1.4 GB 2.7 GB
Fits Get file →
Q5_K_M1.4 GB 2.7 GB
Fits Get file →
Q5_11.4 GB 2.7 GB
Fits Get file →
Q6_K1.6 GB 2.9 GB
Fits Get file →

What GPU do you need for InternLM2?

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: the best quant that fits is Q6_K (1.6 GB file, about 2.9 GB in use).

Which InternLM2 quant should you choose?

Q4_K_M is the usual starting point for InternLM2: it balances file size and quality well. Here it is a 1.2 GB file.

If memory is tight, the smallest file is Q2_K at 0.8 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

Architectureinternlm2
Parameters1.89B
Layers24
Trained context32,768 tokens
KV cache (fp16)96 KB per token

Source

Quantized byRichardErkhov
FamilyInternLM
Downloads (HF)182
Last updated2024-05-09

Frequently asked questions about InternLM2

How much VRAM does InternLM2 need?

About 2.5 GB at Q4_K_M with an 8K context window. That is the 1.2 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 on an 8 GB GPU?

Yes, with Q6_K: the 1.6 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of InternLM2 GGUF?

It depends on the quant: Q2_K is 0.8 GB, IQ3_XS is 0.9 GB, IQ3_S is 0.9 GB, Q3_K_S is 0.9 GB, IQ3_M is 0.9 GB, Q3_K is 1.0 GB and 15 more.

What context length does InternLM2 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download InternLM2 GGUF?

The files are on Hugging Face in the RichardErkhov/internlm_-_internlm2-chat-1_8b-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 RichardErkhov

All by RichardErkhov →

More InternLM models

All InternLM →

Other tiny models

All tiny models →