AN

anah 20b

AnahGGUF by mradermacherUpdated 2025-03-08
Download on Hugging Face
Parameters19.9B
Context32K
Layers48
Architectureinternlm2
Smallest quant7.5 GB
Quick answer

anah 20b needs about 14.1 GB of memory at Q4_K_M (a 12.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 14 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.

Anah 20B – InternLM2 model fine‑tuned for hallucination annotation

Anah 20B is a 19.9 billion‑parameter InternLM2 model trained on the ANAH dataset. It is designed to annotate hallucinations in LLM responses. The model supports a 32 768‑token context window and is released under the Apache‑2.0 license.

Good at

  • Hallucination annotation
  • InternLM2 chat format
  • Large context handling

Limits

  • No vision support
  • Requires 8 k context for memory estimates
  • License is Apache‑2.0

Best for

  • Research on hallucination detection
  • Fine‑tuning for safety analysis
  • Chatbot post‑processing

Who it’s for. Researchers and developers working on LLM safety and hallucination mitigation. The model is suitable for teams that need a large‑context, annotation‑focused LLM and have the resources to run it locally.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K7.5 GB 9.7 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_K_M9.7 GB 11.8 GB
Too big Get file →
Q3_K_L10.6 GB 12.7 GB
Too big Get file →
IQ4_XS10.9 GB 13.0 GB
Too big Get file →
Q4_K_S11.4 GB 13.5 GB
Too big Get file →
Q4_K_M12.0 GB 14.1 GB
Too big Get file →
Q5_K_S13.7 GB 15.8 GB
Too big Get file →
Q5_K_M14.1 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 →

For 8 GB VRAM, use Q2_K (7.55 GB, 9.7 GB memory) or IQ3_XS (8.36 GB, 10.5 GB memory). For 12 GB VRAM, Q4_K_S (11.4 GB, 13.5 GB memory) or Q5_K_S (13.73 GB, 15.8 GB memory) are suitable. Larger VRAM allows higher‑quality quants such as Q6_K (16.3 GB, 18.4 GB memory).

What GPU do you need for anah 20b?

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_M (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 anah 20b quant should you choose?

Q4_K_M is the usual starting point for anah 20b: it balances file size and quality well. Here it is a 12.0 GB file.

The Q8_0 file is 21.1 GB, about 1.8 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 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

Architectureinternlm2
Parameters19.9B
Layers48
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymradermacher
FamilyAnah
Licenseapache-2.0
Downloads (HF)1,063
Last updated2025-03-08

Frequently asked questions about anah 20b

How much VRAM does anah 20b need?

About 14.1 GB at Q4_K_M 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 anah 20b 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 anah 20b GGUF?

It depends on the quant: Q2_K is 7.5 GB, IQ3_XS is 8.4 GB, Q3_K_S is 8.8 GB, IQ3_S is 8.8 GB, IQ3_M is 9.1 GB, Q3_K_M is 9.7 GB and 8 more.

What context length does anah 20b 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 anah 20b GGUF?

The files are on Hugging Face in the mradermacher/anah-20b-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 anah 20b use?

Hugging Face lists the license as apache-2.0. 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 Anah 20B on 8 GB VRAM?

Yes, the Q2_K quant is 7.55 GB and requires about 9.7 GB of VRAM at 8 k context.

Does Anah 20B support image inputs?

No, the model has no vision capabilities.

What license applies to Anah 20B?

The model is released under the Apache‑2.0 license.

Other GGUFs of anah-20b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Anah models

All Anah →

Other medium models

All medium models →