IN

InternLM2

InternLMGGUF by legraphistaUpdated 2024-05-27
Download on Hugging Face
Parameters19.9B
Context8K
Layers48
Architectureinternlm2
Smallest quant4.5 GB
Quick answer

InternLM2 needs about 11.2 GB of memory at IQ3_M (a 9.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 4.5 GB (IQ1_S) to 39.7 GB.

InternLM2-Math-Plus 20B GGUF model for advanced math reasoning

InternLM2-Math-Plus 20B is a 20‑billion‑parameter LLM optimized for math reasoning. It supports 8192‑token context and is available in multiple GGUF quantizations. The model is open‑source and can be run with llama.cpp.

Good at

  • Math problem solving
  • Formal theorem proving
  • Code‑based reasoning

Limits

  • Requires large VRAM for high‑precision quants
  • No vision or audio capabilities
  • License is other, not standard open‑source

Best for

  • Solving algebraic equations
  • Proving mathematical statements
  • Generating code for math tasks

Who it’s for. Developers and researchers needing a high‑performance math LLM that can run locally. The model is suitable for users with sufficient GPU memory to accommodate the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S4.5 GB 6.7 GB
Fits Get file →
IQ1_M4.9 GB 7.0 GB
Fits Get file →
IQ2_XXS5.5 GB 7.7 GB
Tight Get file →
IQ2_XS6.1 GB 8.2 GB
Too big Get file →
IQ2_S6.5 GB 8.6 GB
Too big Get file →
IQ2_M7.0 GB 9.1 GB
Too big Get file →
Q2_K_S7.0 GB 9.1 GB
Too big Get file →
Q2_K7.5 GB 9.7 GB
Too big Get file →
IQ3_XXS7.8 GB 9.9 GB
Too big Get file →
IQ3_XS8.4 GB 10.5 GB
Too big Get file →
Q3_K_S8.8 GB 10.9 GB
Too big Get file →
IQ3_S8.8 GB 10.9 GB
Too big Get file →
IQ3_M9.1 GB 11.2 GB
Too big Get file →
Q3_K9.7 GB 11.8 GB
Too big Get file →
Q3_K_L10.6 GB 12.7 GB
Too big Get file →
IQ4_XS10.8 GB 12.9 GB
Too big Get file →
IQ4_NL11.4 GB 13.5 GB
Too big Get file →
Q4_K_S11.4 GB 13.5 GB
Too big Get file →
Q4_K12.0 GB 14.1 GB
Too big Get file →
Q5_K_S13.7 GB 15.8 GB
Too big Get file →
Q5_K14.1 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 →
BF1639.7 GB 41.8 GB
Too big Get file →
—39.7 GB 41.8 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (4.54 GB, ~6.7 GB RAM). For 12‑GB VRAM, IQ2_S (6.47 GB, ~8.6 GB RAM) or Q2_K_S (7.01 GB, ~9.1 GB RAM). For 24‑GB VRAM, Q4_K (11.98 GB, ~14.1 GB RAM) or higher. 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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is IQ2_XXS (5.5 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q3_K (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).
  • 32 GB VRAM: the best quant that fits is Q8_0 (21.1 GB file, about 23.2 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (39.7 GB file, about 41.8 GB in use).

Which InternLM2 quant should you choose?

IQ3_M (9.1 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 4.5 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
Parameters19.9B
Layers48
Trained context8,192 tokens
KV cache (fp16)192 KB per token

Source

Quantized bylegraphista
FamilyInternLM
Licenseother
Downloads (HF)5,954
Last updated2024-05-27

Frequently asked questions about InternLM2

How much VRAM does InternLM2 need?

About 11.2 GB at IQ3_M with an 8K context window. That is the 9.1 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 IQ2_XXS: the 5.5 GB file needs about 7.7 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 4.5 GB, IQ1_M is 4.9 GB, IQ2_XXS is 5.5 GB, IQ2_XS is 6.1 GB, IQ2_S is 6.5 GB, IQ2_M is 7.0 GB and 19 more.

What context length does InternLM2 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 GGUF?

The files are on Hugging Face in the legraphista/internlm2-math-plus-20b-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-Math-Plus on 8 GB VRAM?

Use the IQ1_S quant, which is 4.54 GB and requires about 6.7 GB VRAM at 8k context.

Does this model support image input?

No, InternLM2-Math-Plus is a text‑only model with no vision capability.

What is the context length of this model?

The model supports up to 8192 tokens of context.

Other GGUFs of internlm2-math-plus-20b

Similar models

Browse all →

More from legraphista

All by legraphista →

More InternLM models

All InternLM →

Other medium models

All medium models →