What are the hardware requirements for Chikuma 10.7B?

Chikuma 10.7B requires approximately 21.4 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 Chikuma 10.7B and how large is it?

Chikuma 10.7B is developed by sethuiyer, a model with 10.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Chikuma 10.7B perform on standard benchmarks?

Chikuma 10.7B has the following published scores: MMLU 64.81. Compare against reference models on this page or on the LLM Explorer leaderboards.

Chikuma 10.7B by sethuiyer — VRAM 21.4GB, 32K context

Name: Chikuma 10.7B
Author: sethuiyer

Chikuma 10.7B is an open-source language model by sethuiyer. Features: 10.7b LLM, VRAM: 21.4GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.12, Arc: 65.7, HellaSwag: 84.3, MMLU: 64.8, GSM8K: 57.6.

Base model:merge:openchat/open... Base model:merge:sethuiyer/syn... Base model:openchat/openchat-3... Base model:sethuiyer/synthiq-7... Conversational En Endpoints compatible Merge Mistral Model-index Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/sethuiyer/Chikuma_10.7B

Chikuma 10.7B Parameters and Internals

Model Type

text-generation

Additional Notes

Chikuma is a combined model created using LazyMergekit from SynthIQ-7b and openchat-3.5-0106 models. It is named after the Chikuma River to metaphorically represent its characteristics. Recommended prompt templates and usage configurations are provided for optimal performance.

LLM Name	Chikuma 10.7B
Repository 🤗	https://huggingface.co/sethuiyer/Chikuma_10.7B
Base Model(s)	SynthIQ 7B openchat/openchat-3.5-0106 sethuiyer/SynthIQ-7b openchat/openchat-3.5-0106
Model Size	10.7b
Required VRAM	21.4 GB
Updated	2026-04-22
Maintainer	sethuiyer
Model Type	mistral
Model Files	9.9 GB: 1-of-3 9.9 GB: 2-of-3 1.6 GB: 3-of-3
Supported Languages	en
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizer
Padding Token	<\|end_of_turn\|>
Vocabulary Size	32002
Torch Data Type	bfloat16

Rank the Chikuma 10.7B 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 Chikuma 10.7B

Best Alternatives	Context / RAM	Downloads	Likes
Barely Regal 10.7B	32K / 21.5 GB	19	0
Quintellect 10.7B	32K / 21.4 GB	22	3
PiVoT 10.7B Mistral V0.2	32K / 21.4 GB	76	5
Longcat 10.7B	32K / 21.5 GB	8	3
Multi Verse Model 10.7B	32K / 21.5 GB	2	1
PrimaSumika 10.7B 128K	32K / 21.5 GB	3	1
... Loyal Mistral Maid 32K V0.2 A	32K / 21.5 GB	3	1
Chikuma 10.7B V2	32K / 21.4 GB	10	0
PiVoT 10.7B Mistral V0.2 RP	32K / 21.4 GB	67	7
Mark1 Revision 10.7B	32K / 42.9 GB	16	1

Note: green Score (e.g. "73.2") means that the model is better than sethuiyer/Chikuma_10.7B.