What are the hardware requirements for Threebird 7B?

Threebird 7B requires approximately 14.5 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Threebird 7B and how large is it?

Threebird 7B is developed by Lambent, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Threebird 7B perform on standard benchmarks?

Threebird 7B has the following published scores: MMLU 65.02. Compare against reference models on this page or on the LLM Explorer leaderboards.

Threebird 7B by Lambent — VRAM 14.5GB, 32K context

Name: Threebird 7B
Author: Lambent

Threebird 7B is an open-source language model by Lambent. Features: 7b LLM, VRAM: 14.5GB, Context: 32K, License: apache-2.0, Code Generating, Merged, LLM Explorer Score: 0.13, Arc: 72.4, HellaSwag: 87.8, MMLU: 65, GSM8K: 71.7.

Merged Model Arxiv:2306.01708 Base model:bobofrut/ladybird-b... Base model:macadeliccc/westlak... Base model:mistralai/mistral-7... Base model:s-miguel/the-trinit... Codegen Endpoints compatible Mistral Model-index Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Lambent/threebird-7B

Threebird 7B Parameters and Internals

Model Type

text-generation

Additional Notes

This model is a merge created using the TIES method involving S-miguel/The-Trinity-Coder-7B, macadeliccc/WestLake-7B-v2-laser-truthy-dpo, and bobofrut/ladybird-base-7B-v8 models with mistralai/Mistral-7B-v0.1 as base.

LLM Name	Threebird 7B
Repository 🤗	https://huggingface.co/Lambent/threebird-7B
Base Model(s)	The Trinity Coder 7B ...estLake 7B V2 Laser Truthy DPO mistralai/Mistral-7B-v0.1 Ladybird Base 7B V8 S-miguel/The-Trinity-Coder-7B macadeliccc/WestLake-7B-v2-laser-truthy-dpo mistralai/Mistral-7B-v0.1 bobofrut/ladybird-base-7B-v8
Merged Model	Yes
Model Size	7b
Required VRAM	14.5 GB
Updated	2026-04-27
Maintainer	Lambent
Model Type	mistral
Model Files	4.9 GB: 1-of-3 4.9 GB: 2-of-3 4.7 GB: 3-of-3
Generates Code	Yes
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.41.0.dev0
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	float16

Rank the Threebird 7B 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 Threebird 7B

Best Alternatives	Context / RAM	Downloads	Likes
SpydazWeb AI HumanAI RP	512K / 14.4 GB	16	1
SpydazWeb AI HumanAI 002	512K / 14.4 GB	18	1
Lexi Coder V5.1	32K / 14.5 GB	197	0
Mistral 7B Merged	32K / 14.5 GB	6	0
RP Coder SM3	32K / 14.5 GB	65	0
Jett W26 Abliterated	32K / 14.4 GB	8	1
Jett W26	32K / 14.5 GB	5	1
Ultra Llm Merged	32K / 14.5 GB	7	0
The Trinity Coder 7B	32K / 14.4 GB	63	6
MonarchCoder 7B	32K / 14.4 GB	72	1

Note: green Score (e.g. "73.2") means that the model is better than Lambent/threebird-7B.