IN

InternLM2

InternLMGGUF by bartowskiUpdated 2024-07-03
Download on Hugging Face
Parameters7.74B
Context256K
Layers32
Architectureinternlm2
Smallest quant2.5 GB
Quick answer

InternLM2 needs about 6.3 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 2.5 GB (IQ2_XS) to 31.0 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

InternLM2 7.74B chat model in GGUF format

InternLM2 is a 7.74B parameter chat model with a trained context of 262144 tokens. The GGUF files are quantized by bartowski and available in a range of precision options. The model is part of the InternLM family and uses the internlm2 architecture.

Good at

  • Large context handling
  • Chat‑ready responses
  • Versatile quantization options

Limits

  • No vision support
  • License type is other
  • No mixture of experts

Best for

  • Chatbot development
  • Context‑heavy dialogue systems
  • Low‑memory inference

Who it’s for. Developers needing a large‑context chat model that can be run on a variety of GPU and CPU setups. The model supports multiple quantizations, allowing selection based on available memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XS2.5 GB 4.0 GB
Fits Get file →
IQ2_S2.6 GB 4.2 GB
Fits Get file →
IQ2_M2.8 GB 4.4 GB
Fits Get file →
Q2_K3.0 GB 4.6 GB
Fits Get file →
IQ3_XXS3.1 GB 4.7 GB
Fits Get file →
IQ3_XS3.3 GB 4.9 GB
Fits Get file →
Q3_K_S3.5 GB 5.0 GB
Fits Get file →
IQ3_M3.6 GB 5.2 GB
Fits Get file →
Q3_K_M3.8 GB 5.4 GB
Fits Get file →
Q2_K_L4.1 GB 5.7 GB
Fits Get file →
Q3_K_L4.1 GB 5.7 GB
Fits Get file →
IQ4_XS4.2 GB 5.8 GB
Fits Get file →
Q4_K_S4.5 GB 6.1 GB
Fits Get file →
Q4_K_M4.7 GB 6.3 GB
Fits Get file →
Q3_K_XL5.2 GB 6.7 GB
Fits Get file →
Q5_K_S5.4 GB 6.9 GB
Fits Get file →
Q5_K_M5.5 GB 7.1 GB
Fits Get file →
Q4_K_L5.7 GB 7.3 GB
Tight Get file →
Q6_K6.4 GB 7.9 GB
Tight Get file →
Q5_K_L6.5 GB 8.0 GB
Too big Get file →
Q6_K_L7.2 GB 8.8 GB
Too big Get file →
Q8_08.2 GB 9.8 GB
Too big Get file →
Q8_08.9 GB 10.5 GB
Too big Get file →
F3231.0 GB 32.5 GB
Too big Get file →

For 8 GB VRAM, use IQ2_S (2.59 GB) or Q2_K (3.01 GB). For 12 GB VRAM, Q4_K_S (4.48 GB) or Q4_K_M (4.71 GB) fit comfortably. For 16 GB VRAM, Q5_K_M (5.51 GB) or Q6_K (6.35 GB) are suitable. Memory estimates are approximate.

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 IQ2_XS (2.5 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_XS (4.2 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_L (6.5 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 10.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 10.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 10.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 10.5 GB in use).
  • 48 GB VRAM: the best quant that fits is F32 (31.0 GB file, about 32.5 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 4.7 GB file.

The Q8_0 file is 8.2 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 IQ2_XS at 2.5 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
Parameters7.74B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized bybartowski
FamilyInternLM
Licenseother
Downloads (HF)676
Last updated2024-07-03

Frequently asked questions about InternLM2

How much VRAM does InternLM2 need?

About 6.3 GB at Q4_K_M with an 8K context window. That is the 4.7 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 Q5_K_L: the 6.5 GB file needs about 8.0 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: IQ2_XS is 2.5 GB, IQ2_S is 2.6 GB, IQ2_M is 2.8 GB, Q2_K is 3.0 GB, IQ3_XXS is 3.1 GB, IQ3_XS is 3.3 GB and 18 more.

What context length does InternLM2 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download InternLM2 GGUF?

The files are on Hugging Face in the bartowski/internlm2_5-7b-chat-1m-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 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.

Can I run InternLM2 on 8 GB VRAM?

Yes, use a quant such as IQ2_S or Q2_K, which are under 4 GB of VRAM usage.

Does InternLM2 support vision tasks?

No, the model has no vision capabilities.

What is the maximum context length for this model?

The trained context is 262144 tokens.

Similar models

Browse all →

More from bartowski

All by bartowski →

More InternLM models

All InternLM →

Other small models

All small models →