What are the hardware requirements for Cisco INAM 1.1B?

Cisco INAM 1.1B requires approximately 0.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Cisco INAM 1.1B and how large is it?

Cisco INAM 1.1B is developed by ndavidson, a model with 1.1b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Cisco INAM 1.1B perform on standard benchmarks?

Cisco INAM 1.1B has the following published scores: MMLU 26.39. Compare against reference models on this page or on the LLM Explorer leaderboards.

Cisco INAM 1.1B by ndavidson — VRAM 0.1GB

Name: Cisco INAM 1.1B
Author: ndavidson

Cisco INAM 1.1B is an open-source language model by ndavidson. Features: 1.1b LLM, VRAM: 0.1GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.16, Arc: 36, HellaSwag: 60.7, MMLU: 26.4, GSM8K: 1.4.

4bit Base model:quantized:unsloth/t... Base model:unsloth/tinyllama-b... Conversational En Endpoints compatible Gguf Llama Lora Quantized Region:us Safetensors Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/ndavidson/cisco-iNAM-1.1B

Cisco INAM 1.1B Parameters and Internals

Model Type

text-generation-inference, transformers, unsloth, llama, trl

Additional Notes

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Training Details

Methodology:

Unsloth and Huggingface's TRL library

LLM Name	Cisco INAM 1.1B
Repository 🤗	https://huggingface.co/ndavidson/cisco-iNAM-1.1B
Base Model(s)	Tinyllama Bnb 4bit unsloth/tinyllama-bnb-4bit
Model Size	1.1b
Required VRAM	0.1 GB
Updated	2026-07-26
Maintainer	ndavidson
Model Files	0.1 GB 0.7 GB
Supported Languages	en
GGUF Quantization	Yes
Quantization Type	gguf\|4bit
Model Architecture	AutoModel
License	apache-2.0
Is Biased	none
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	k_proj\|up_proj\|gate_proj\|down_proj\|v_proj\|o_proj\|q_proj
LoRA Alpha	32
LoRA Dropout	0
R Param	32

Rank the Cisco INAM 1.1B 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 Cisco INAM 1.1B

Best Alternatives	Context / RAM	Downloads	Likes
TinyLlama 1.1B Chat V1.0 GGUF	0K / 0.5 GB	143745	233
TinyLlama 1.1B Chat V0.3 GGUF	0K / 0.5 GB	41141	48
TinyLlama 1.1B Gguf Unsloth	0K / 0.7 GB	31	1
TiamaPY 1.1B V24 Q8 0 GGUF	0K / 1.2 GB	10	0
Tinyllama Coder Py 4bit V9	0K / 0.7 GB	27	0
Tinyllama Coder Py 4bit V8	0K / 0.7 GB	29	0
Tinyllama Coder Py 4bit V7	0K / 0.7 GB	20	0
Tinyllama Coder Py 4bit V5	0K / 1.2 GB	18	0
Tinyllama Coder Py 4bit V6	0K / 1.2 GB	15	0
Tinyllama Coder Py 4bit V2	0K / 0.7 GB	17	0

Note: green Score (e.g. "73.2") means that the model is better than ndavidson/cisco-iNAM-1.1B.