What are the hardware requirements for 10.5B V1?

10.5B V1 requires approximately 20.7 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 10.5B V1 and how large is it?

10.5B V1 is developed by coldint, a model with 10.5b 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 10.5B V1?

10.5B V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

10.5B V1 by coldint — VRAM 20.7GB, 4K context

Name: 10.5B V1
Author: coldint

10.5B V1 is an open-source language model by coldint. Features: 10.5b LLM, VRAM: 20.7GB, Context: 4K, Merged, LLM Explorer Score: 0.14.

Merged Model Arxiv:1910.09700 Conversational Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/coldint/10.5B_v1

10.5B V1 Parameters and Internals

LLM Name	10.5B V1
Repository 🤗	https://huggingface.co/coldint/10.5B_v1
Merged Model	Yes
Model Size	10.5b
Required VRAM	20.7 GB
Updated	2026-08-05
Maintainer	coldint
Model Type	llama
Model Files	4.9 GB: 1-of-5 5.0 GB: 2-of-5 5.0 GB: 3-of-5 5.0 GB: 4-of-5 0.8 GB: 5-of-5
Model Architecture	LlamaForCausalLM
Context Length	4096
Model Max Length	4096
Transformers Version	4.44.0
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	96000
Torch Data Type	bfloat16

Rank the 10.5B 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 10.5B V1

Best Alternatives	Context / RAM	Downloads	Likes
St Vicuna V1.3 10.5B Ppl	2K / 20.9 GB	13	9
St Vicuna V1.3 10.5B Taylor	2K / 20.9 GB	6	9
FRS Sum	0.5K / 0 GB	246	1

Note: green Score (e.g. "73.2") means that the model is better than coldint/10.5B_v1.