DiarizationLM 13b Fisher v1 needs about 15.1 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 7.9 GB (Q4_K_M) to 13.8 GB (Q8_0).
DiarizationLM 13b Fisher v1 – a fine‑tuned 13B Llama model for speaker diarization
DiarizationLM 13b Fisher v1 is a 13B llama architecture model fine‑tuned on the Fisher corpus using a LoRA adapter. It was trained for 12000 steps on an A100 GPU with 80GB memory. The model is not officially supported by Google.
Good at
- Speaker diarization on Fisher data
- Fine‑tuned Llama 2 architecture
- LoRA‑adapted performance
Limits
- No vision support
- Limited to 4096 context tokens
- Not officially supported by Google
Best for
- Audio transcription with speaker tags
- Research on diarization datasets
- Fine‑tuning for specific speaker sets
Who it’s for. Researchers and developers needing a 13B Llama model fine‑tuned for speaker diarization. Suitable for academic projects or prototyping where official support is not required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 7.9 GB | 11.7 GB | Too big | Get file → | |
| Q8_0 | 13.8 GB | 17.7 GB | Too big | Get file → |
For 8 GB VRAM use the Q4_K_M quant file (7.87 GB, ~15.1 GB memory at 8k context). For 12 GB VRAM use Q8_0 (13.83 GB, ~21 GB memory at 8k context). Memory estimates are approximate.
What GPU do you need for DiarizationLM 13b Fisher 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: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q4_K_M (7.9 GB file, about 15.1 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).
Which DiarizationLM 13b Fisher v1 quant should you choose?
Q4_K_M is the usual starting point for DiarizationLM 13b Fisher v1: it balances file size and quality well. Here it is a 7.9 GB file.
The Q8_0 file is 13.8 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about DiarizationLM 13b Fisher v1
How much VRAM does DiarizationLM 13b Fisher v1 need?
About 15.1 GB at Q4_K_M with an 8K context window. That is the 7.9 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 13b Fisher v1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of DiarizationLM 13b Fisher v1 GGUF?
It depends on the quant: Q4_K_M is 7.9 GB, Q8_0 is 13.8 GB.
What context length does DiarizationLM 13b Fisher v1 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.
Where can I download DiarizationLM 13b Fisher v1 GGUF?
The files are on Hugging Face in the google/DiarizationLM-13b-Fisher-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 13b Fisher v1 use?
Hugging Face lists the license as llama2. 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 DiarizationLM 13b Fisher v1 on 8 GB VRAM?
Yes, using the Q4_K_M quantized file (7.87 GB). It requires about 15.1 GB of VRAM at 8k context, so 8 GB VRAM is insufficient. Use a higher VRAM GPU or a smaller quant.
Is this model officially supported by Google?
No. The model is not an officially supported Google product and is marked as outdated.
What context length does this model support?
It supports up to 4096 tokens of context.