What are the hardware requirements for DiarizationLM 13B Fisher V1?

DiarizationLM 13B Fisher V1 requires approximately 26 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed DiarizationLM 13B Fisher V1 and how large is it?

DiarizationLM 13B Fisher V1 is developed by google, a model with 13b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate DiarizationLM 13B Fisher V1?

DiarizationLM 13B Fisher V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

DiarizationLM 13B Fisher V1 by google — VRAM 26GB, 4K context

Name: DiarizationLM 13B Fisher V1
Author: google

DiarizationLM 13B Fisher V1 is an open-source language model by google. Features: 13b LLM, VRAM: 26GB, Context: 4K, License: llama2, Quantized, LLM Explorer Score: 0.14.

Arxiv:2401.03506 4bit Endpoints compatible Gguf Llama Q4 Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/google/DiarizationLM-13b-Fisher-v1

DiarizationLM 13B Fisher V1 Parameters and Internals

Model Type

Speaker Diarization, Causal Language Model

Use Cases

Areas:

Research applications

Additional Notes

This model is outdated. Please use google/DiarizationLM-8b-Fisher-v2 instead.

Training Details

Data Sources:

Fisher corpus

Data Volume:

48,142 prompt-completion pairs

Methodology:

Finetuning a foundation model using LoRA adapter

Context Length:

4096

Training Time:

More than 3 days

Hardware Used:

Google Cloud VM instance with one NVIDIA A100 GPU (80GB)

LLM Name	DiarizationLM 13B Fisher V1
Repository 🤗	https://huggingface.co/google/DiarizationLM-13b-Fisher-v1
Model Size	13b
Required VRAM	26 GB
Updated	2026-08-06
Maintainer	google
Model Type	llama
Model Files	5.0 GB: 1-of-6 5.0 GB: 2-of-6 5.0 GB: 3-of-6 4.9 GB: 4-of-6 4.9 GB: 5-of-6 1.2 GB: 6-of-6 7.9 GB 13.8 GB
GGUF Quantization	Yes
Quantization Type	gguf\|q4\|4bit\|q4_k
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.41.2
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the DiarizationLM 13B Fisher V1 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to DiarizationLM 13B Fisher V1

Best Alternatives	Context / RAM	Downloads	Likes
Llm Compiler 13B Ftd GGUF	16K / 4.8 GB	200	0
Llm Compiler 13B GGUF	16K / 4.8 GB	71	0
Llm Compiler 13B Ftd GGUF	16K / 4.8 GB	60	0
Llm Compiler 13B GGUF	16K / 4.8 GB	13	0
CodeLlama 13B Instruct GGUF	16K / 5.4 GB	611	2
Luminia 13B V3	4K / 26 GB	83	6
Mythomax L2 13B Q4 K M GGUF	4K / 8.1 GB	1928	12
HyperLlama2Test	4K / 26 GB	16	0
...V2 13B L2 BetaTest Q4 K M GGUF	4K / 7.9 GB	37	0
...Llama 2 13B Fast Instruct GGUF	4K / 5.5 GB	816	1

Note: green Score (e.g. "73.2") means that the model is better than google/DiarizationLM-13b-Fisher-v1.