ME

Medgemma 4b It Abliterated

MedgemmaGGUF by mradermacherUpdated 2025-07-22
Download on Hugging Face
Parameters3.88B
Context128K
Layers34
Architecturegemma3
Smallest quant1.1 GB
Quick answer

Medgemma 4b It Abliterated needs about 4.1 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 1.1 GB (IQ1_S) to 3.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.

Medgemma 4b It Abliterated – a 3.88B parameter medical instruction model

Medgemma 4b It Abliterated is a 3.88B parameter gemma3 model fine‑tuned for medical instruction following. It has undergone an abliteration process to reduce harmful content and was further LoRA‑fine‑tuned with Axolotl. The model supports up to 131072 context tokens and is released under Apache‑2.0.

Good at

  • Medical instruction following
  • Safe medical content generation
  • Research on harm mitigation

Limits

  • No vision support
  • Not a medical professional substitute
  • Large VRAM required for higher quants

Best for

  • Medical Q&A assistants
  • Clinical research prototypes
  • Medical content moderation studies

Who it’s for. Developers building medical chatbots or research tools that need instruction‑following LLMs with reduced harmful behavior. The model is suitable for teams that can provide professional medical oversight and have sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.1 GB 2.8 GB
Fits Get file →
IQ1_M1.2 GB 2.8 GB
Fits Get file →
IQ2_XXS1.3 GB 3.0 GB
Fits Get file →
IQ2_XS1.4 GB 3.0 GB
Fits Get file →
IQ2_S1.4 GB 3.1 GB
Fits Get file →
IQ2_M1.5 GB 3.2 GB
Fits Get file →
Q2_K_S1.6 GB 3.3 GB
Fits Get file →
IQ3_XXS1.7 GB 3.3 GB
Fits Get file →
Q2_K1.7 GB 3.4 GB
Fits Get file →
IQ3_XS1.9 GB 3.5 GB
Fits Get file →
IQ3_S1.9 GB 3.6 GB
Fits Get file →
Q3_K_S1.9 GB 3.6 GB
Fits Get file →
IQ3_M2.0 GB 3.6 GB
Fits Get file →
Q3_K_M2.1 GB 3.7 GB
Fits Get file →
Q3_K_L2.2 GB 3.9 GB
Fits Get file →
IQ4_XS2.3 GB 3.9 GB
Fits Get file →
IQ4_NL2.4 GB 4.0 GB
Fits Get file →
Q4_02.4 GB 4.0 GB
Fits Get file →
Q4_K_S2.4 GB 4.0 GB
Fits Get file →
Q4_K_M2.5 GB 4.1 GB
Fits Get file →
Q4_12.6 GB 4.2 GB
Fits Get file →
Q5_K_S2.8 GB 4.4 GB
Fits Get file →
Q5_K_M2.8 GB 4.5 GB
Fits Get file →
Q6_K3.2 GB 4.8 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S or IQ1_M (≈2.8 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (≈4.1 GB) or Q5_K_M (≈4.5 GB) are suitable. Larger VRAM allows Q6_K (≈4.8 GB).

What GPU do you need for Medgemma 4b It Abliterated?

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 Q4_K_S (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.2 GB file, about 4.8 GB in use).

Which Medgemma 4b It Abliterated quant should you choose?

Q4_K_M is the usual starting point for Medgemma 4b It Abliterated: it balances file size and quality well. Here it is a 2.5 GB file.

If memory is tight, the smallest file is IQ1_S at 1.1 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

Architecturegemma3
Parameters3.88B
Layers34
Trained context131,072 tokens
KV cache (fp16)136 KB per token

Source

Quantized bymradermacher
FamilyMedgemma
Licenseapache-2.0
Downloads (HF)382
Last updated2025-07-22

Frequently asked questions about Medgemma 4b It Abliterated

How much VRAM does Medgemma 4b It Abliterated need?

About 4.1 GB at Q4_K_M with an 8K context window. That is the 2.5 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 Medgemma 4b It Abliterated on an 8 GB GPU?

Yes, with Q6_K: the 3.2 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Medgemma 4b It Abliterated GGUF?

It depends on the quant: IQ1_S is 1.1 GB, IQ1_M is 1.2 GB, IQ2_XXS is 1.3 GB, IQ2_XS is 1.4 GB, IQ2_S is 1.4 GB, IQ2_M is 1.5 GB and 18 more.

What context length does Medgemma 4b It Abliterated support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.6 GB at 32K.

Where can I download Medgemma 4b It Abliterated GGUF?

The files are on Hugging Face in the mradermacher/medgemma-4b-it-abliterated-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 Medgemma 4b It Abliterated 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 Medgemma 4b It Abliterated on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quant, which require about 2.8 GB memory at 8 k context.

Does this model support vision inputs?

No, this model is text‑only; vision support is not available.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of medgemma-4b-it-abliterated

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Medgemma models

All Medgemma →

Other small models

All small models →