What are the hardware requirements for Llama3Ternary 10B?

Llama3Ternary 10B requires approximately 2.8 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama3Ternary 10B and how large is it?

Llama3Ternary 10B is developed by CMSManhattan, a model with 8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Llama3Ternary 10B perform on standard benchmarks?

Llama3Ternary 10B has the following published scores: MMLU 66.49. Compare against reference models on this page or on the LLM Explorer leaderboards.

Llama3Ternary 10B by CMSManhattan — VRAM 2.8GB, 8K context

Name: Llama3Ternary 10B
Author: CMSManhattan

Llama3Ternary 10B is an open-source language model by CMSManhattan. Features: 8b LLM, VRAM: 2.8GB, Context: 8K, License: llama3, Quantized, LLM Explorer Score: 0.35, Arc: 59.2, HellaSwag: 82, MMLU: 66.5, GSM8K: 45.3.

1.58bit Base model:meta-llama/meta-lla... Base model:quantized:meta-llam... Bitnet Conversational En Endpoints compatible Gguf Llama Q8 Quantized Region:us Safetensors Ternary

Model Card on HF 🤗: https://huggingface.co/CMSManhattan/Llama3Ternary_10b

Llama3Ternary 10B Parameters and Internals

LLM Name	Llama3Ternary 10b
Repository 🤗	https://huggingface.co/CMSManhattan/Llama3Ternary_10b
Base Model(s)	Meta Llama 3 8B meta-llama/Meta-Llama-3-8B
Model Size	8b
Required VRAM	2.8 GB
Updated	2026-10-09
Maintainer	CMSManhattan
Model Type	llama
Model Files	11.2 GB 4.3 GB 19.3 GB 4.1 GB 4.1 GB 4.1 GB 4.1 GB 2.8 GB
Supported Languages	en
GGUF Quantization	Yes
Quantization Type	gguf\|q8
Model Architecture	LlamaForCausalLM
License	llama3
Context Length	8192
Model Max Length	8192
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	128256
Torch Data Type	float16

Rank the Llama3Ternary 10B 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 Llama3Ternary 10B

Best Alternatives	Context / RAM	Downloads	Likes
10K V6	1024K / 16.1 GB	5	0
...truct Gradient 1048K IMat GGUF	1024K / 2 GB	650	6
...B Instruct Gradient 1048K GGUF	1024K / 3.2 GB	445	3
Unhinged Llama3 8B 524K	512K / 26.5 GB	25	0
Llama 3 8B Instruct 262K GGUF	256K / 3.2 GB	208	2
Dolphin3 Cyber 8B GGUF	128K / 3.2 GB	59950	150
Grok Oss Apollyon 8B	128K / 16.1 GB	3449	8
...s Abliterated V2 Base And GGUF	128K / 16.1 GB	301	2
Dolphin3 Cyber 8B GGUF	128K / 3.2 GB	456	1
Grok Oss Revenant 8B	128K / 16.1 GB	324	0