internLM needs about 14.1 GB of memory at Q4_K (a 12.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 6 quants, from 7.5 GB (Q2_K) to 21.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
internLM is a 19.9B-parameter InternLM model in GGUF format, quantized by Aculi. Its trained context length is 32K tokens. The repository has 6 quant files, from 7.5 GB (Q2_K) to 21.1 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 7.5 GB | 9.7 GB | Too big | Get file → | |
| Q3_K | 9.7 GB | 11.8 GB | Too big | Get file → | |
| Q4_K | 12.0 GB | 14.1 GB | Too big | Get file → | |
| Q5_K_S | 13.7 GB | 15.8 GB | Too big | Get file → | |
| Q6_K | 16.3 GB | 18.4 GB | Too big | Get file → | |
| Q8_0 | 21.1 GB | 23.2 GB | Too big | Get file → |
What GPU do you need for internLM?
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: 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).
Which internLM quant should you choose?
Q4_K (12.0 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is Q2_K at 7.5 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
Source
Frequently asked questions about internLM
How much VRAM does internLM need?
About 14.1 GB at Q4_K 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 internLM on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of internLM GGUF?
It depends on the quant: Q2_K is 7.5 GB, Q3_K is 9.7 GB, Q4_K is 12.0 GB, Q5_K_S is 13.7 GB, Q6_K is 16.3 GB, Q8_0 is 21.1 GB.
What context length does internLM 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 internLM GGUF?
The files are on Hugging Face in the Aculi/InternLM2-Chat-20B-ToxicRP-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.