DiarizationLM Gemma 4 E4B v1 needs about 7.2 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.
Gemma 4 E4B fine‑tuned for speaker diarization and ASR post‑processing
DiarizationLM Gemma 4 E4B v1 is a 7.46B parameter model built on google/gemma-4-E4B. It is trained to correct and optimize ASR and speaker diarization outputs using locality‑preserving oracle supervision. The model supports multimodal input and has a 131072 token context window.
Good at
- Speaker diarization post‑processing
- ASR output correction
- Multimodal reasoning
Limits
- No vision support in this fine‑tuned version
- Requires 8.2 GB VRAM for Q4_K_M
- Large context window may exceed typical device limits
Best for
- Post‑processing ASR transcripts
- Speaker diarization refinement
- Multimodal dialogue systems
Who it’s for. Developers building ASR pipelines who need accurate speaker turn detection and lexical correction. Researchers working on multimodal dialogue and speaker identification tasks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 5.3 GB | 7.2 GB | Tight | Get file → |
For 8 GB VRAM use Q4_K_M (5.3 GB file, ~7.2 GB memory at 8 k context). If more VRAM is available, higher precision quants can be used, but only Q4_K_M is listed.
What GPU do you need for DiarizationLM Gemma 4 E4B v1?
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 Q4_K_M (5.3 GB file, about 7.2 GB in use).
Which DiarizationLM Gemma 4 E4B v1 quant should you choose?
Q4_K_M is the usual starting point for DiarizationLM Gemma 4 E4B v1: it balances file size and quality well. Here it is a 5.3 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about DiarizationLM Gemma 4 E4B v1
How much VRAM does DiarizationLM Gemma 4 E4B v1 need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.3 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 DiarizationLM Gemma 4 E4B v1 on an 8 GB GPU?
Yes, with Q4_K_M: the 5.3 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of DiarizationLM Gemma 4 E4B v1 GGUF?
It depends on the quant: Q4_K_M is 5.3 GB.
What context length does DiarizationLM Gemma 4 E4B v1 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.
Where can I download DiarizationLM Gemma 4 E4B v1 GGUF?
The files are on Hugging Face in the diarizers-community/DiarizationLM-Gemma-4-E4B-v1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does DiarizationLM Gemma 4 E4B v1 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 this model on 8 GB VRAM?
Yes, the Q4_K_M quant uses 5.3 GB file size and requires about 7.2 GB VRAM at 8 k context.
Does this model support vision input?
No, the fine‑tuned version does not include vision capabilities.
What license applies to this model?
The model is released under the Apache 2.0 license.