ME

Medchator 2x7b i1

MedchatorGGUF by mradermacherUpdated 2024-11-03
Download on Hugging Face
Parameters11.1B
Context4K
Layers32
Architecturellama
Smallest quant2.4 GB
Quick answer

Medchator 2x7b i1 needs about 11.5 GB of memory at Q4_K_M (a 6.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 2.4 GB (IQ1_S) to 9.1 GB (Q6_K).

Medchator 2x7b i1 – a 11.1B parameter Mixure of Experts model in GGUF format

Medchator 2x7b i1 is a 11.1B parameter Llama‑based Mixure of Experts model. It was quantized by mradermacher and released under the apache‑2.0 license. The model supports a 4096 token context window.

Good at

  • Medical dialogue
  • Clinical question answering
  • Expertise in specialized domains

Limits

  • No vision support
  • Requires 8k context for full performance
  • Large VRAM needed for higher‑quality quants

Best for

  • Medical chatbot deployments
  • Clinical research assistants
  • Healthcare knowledge bases

Who it’s for. Developers building medical LLM applications who need a specialized Mixure of Experts model. The model is suitable for teams with access to GPU resources that can handle the memory requirements of the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.4 GB 5.0 GB
Fits Get file →
IQ1_M2.6 GB 5.3 GB
Fits Get file →
IQ2_XXS3.0 GB 5.6 GB
Fits Get file →
IQ2_XS3.3 GB 5.9 GB
Fits Get file →
IQ2_S3.5 GB 6.1 GB
Fits Get file →
IQ2_M3.8 GB 6.4 GB
Fits Get file →
Q2_K4.1 GB 6.7 GB
Fits Get file →
IQ3_XXS4.2 GB 6.9 GB
Fits Get file →
IQ3_XS4.6 GB 7.2 GB
Tight Get file →
IQ3_S4.8 GB 7.5 GB
Tight Get file →
Q3_K_S4.8 GB 7.5 GB
Tight Get file →
IQ3_M5.0 GB 7.6 GB
Tight Get file →
Q3_K_M5.4 GB 8.0 GB
Too big Get file →
Q3_K_L5.8 GB 8.5 GB
Too big Get file →
IQ4_XS5.9 GB 8.6 GB
Too big Get file →
Q4_06.3 GB 8.9 GB
Too big Get file →
Q4_06.3 GB 8.9 GB
Too big Get file →
Q4_06.3 GB 8.9 GB
Too big Get file →
Q4_06.3 GB 8.9 GB
Too big Get file →
Q4_K_S6.3 GB 9.0 GB
Too big Get file →
Q4_K_M6.7 GB 9.4 GB
Too big Get file →
Q5_K_S7.6 GB 10.3 GB
Too big Get file →
Q5_K_M7.9 GB 10.5 GB
Too big Get file →
Q6_K9.1 GB 11.7 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 2.4 GB, estimated memory 7.2 GB). For 12 GB VRAM, IQ3_M (file size 5 GB, estimated memory 9.8 GB) offers a good balance of size and quality. For 16 GB VRAM, Q4_K_M (file size 6.7 GB, estimated memory 11.5 GB) provides higher fidelity.

What GPU do you need for Medchator 2x7b i1?

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 (3.0 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (6.7 GB file, about 11.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (9.1 GB file, about 13.9 GB in use).

Which Medchator 2x7b i1 quant should you choose?

Q4_K_M is the usual starting point for Medchator 2x7b i1: it balances file size and quality well. Here it is a 6.7 GB file.

If memory is tight, the smallest file is IQ1_S at 2.4 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

Architecturellama
Parameters11.1B (approximate, mixture of experts)
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyMedchator
Licenseapache-2.0
Downloads (HF)1,058
Last updated2024-11-03

Frequently asked questions about Medchator 2x7b i1

How much VRAM does Medchator 2x7b i1 need?

About 11.5 GB at Q4_K_M with an 8K context window. That is the 6.7 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 Medchator 2x7b i1 on an 8 GB GPU?

Yes, with IQ2_XXS: the 3.0 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Medchator 2x7b i1 GGUF?

It depends on the quant: IQ1_S is 2.4 GB, IQ1_M is 2.6 GB, IQ2_XXS is 3.0 GB, IQ2_XS is 3.3 GB, IQ2_S is 3.5 GB, IQ2_M is 3.8 GB and 18 more.

What context length does Medchator 2x7b i1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download Medchator 2x7b i1 GGUF?

The files are on Hugging Face in the mradermacher/Medchator-2x7b-i1-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 Medchator 2x7b i1 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 Medchator 2x7b i1 on 8 GB VRAM?

Yes, the IQ1_S quant uses about 7.2 GB of VRAM at 8k context, which fits within 8 GB.

Does the model support vision tasks?

No, Medchator 2x7b i1 does not include vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of Medchator-2x7b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Medchator models

All Medchator →

Other medium models

All medium models →