IN

InternLM2

InternLMGGUF by legraphistaUpdated 2024-07-03
Download on Hugging Face
Parameters7.74B
Context256K
Layers32
Architectureinternlm2
Smallest quant1.9 GB
Quick answer

InternLM2 needs about 5.2 GB of memory at IQ3_M (a 3.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 1.9 GB (IQ1_S) to 15.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

InternLM2 7.74B chat model with 1M context

InternLM2 7.74B chat model supports a 1M token context window. It is quantized in multiple formats for different memory budgets. The model is available as a GGUF file from the legraphista repository.

Good at

  • Large context handling
  • Reasoning tasks
  • Tool‑use support

Limits

  • No vision support
  • License is other
  • Requires 8k context for memory estimates

Best for

  • Long‑document summarization
  • Information retrieval from large texts
  • Chat applications needing 1M context

Who it’s for. Developers building chat or retrieval systems that need a 1M token context window. The model is suitable for applications that can handle the memory requirements of the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.9 GB 3.4 GB
Fits Get file →
IQ1_M2.0 GB 3.6 GB
Fits Get file →
IQ2_XXS2.2 GB 3.8 GB
Fits Get file →
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_K_S2.8 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_S3.5 GB 5.1 GB
Fits Get file →
IQ3_M3.6 GB 5.2 GB
Fits Get file →
Q3_K3.8 GB 5.4 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 →
IQ4_NL4.5 GB 6.0 GB
Fits Get file →
Q4_K_S4.5 GB 6.1 GB
Fits Get file →
Q4_K4.7 GB 6.3 GB
Fits Get file →
Q5_K_S5.4 GB 6.9 GB
Fits Get file →
Q5_K5.5 GB 7.1 GB
Fits Get file →
Q6_K6.4 GB 7.9 GB
Tight Get file →
Q8_08.2 GB 9.8 GB
Too big Get file →
BF1615.5 GB 17.1 GB
Too big Get file →
—15.5 GB 17.1 GB
Too big Get file →

For 8‑GB VRAM use IQ1_S (1.87 GB file, 3.4 GB memory at 8k). For 12‑GB VRAM use IQ2_S (2.59 GB file, 4.2 GB memory). For 24‑GB VRAM use Q6_K (6.35 GB file, 7.9 GB memory).

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_NL (4.5 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.4 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.2 GB file, about 9.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.2 GB file, about 9.8 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (15.5 GB file, about 17.1 GB in use).

Which InternLM2 quant should you choose?

IQ3_M (3.6 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_S at 1.9 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 bylegraphista
FamilyInternLM
Licenseother
Downloads (HF)584
Last updated2024-07-03

Frequently asked questions about InternLM2

How much VRAM does InternLM2 need?

About 5.2 GB at IQ3_M with an 8K context window. That is the 3.6 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 6.4 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 InternLM2 GGUF?

It depends on the quant: IQ1_S is 1.9 GB, IQ1_M is 2.0 GB, IQ2_XXS is 2.2 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.6 GB, IQ2_M is 2.8 GB and 19 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 legraphista/internlm2_5-7b-chat-1m-IMat-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, using the IQ1_S quantization which requires about 3.4 GB of VRAM at 8k context.

What is the largest context window supported?

The model supports up to 262144 tokens, effectively a 1M‑token context window.

Does the model support vision tasks?

No, the model has no vision capabilities.

Other GGUFs of internlm2_5-7b-chat-1m

Similar models

Browse all →

More from legraphista

All by legraphista →

More InternLM models

All InternLM →

Other small models

All small models →