Model Comparison

janhq/jan-v3-4b-base-instruct-ggufvsmradermacher/llm-surgery-dark-arts-gpt-oss-60b-96a12-i1-gguf

Side-by-side comparison of janhq/jan-v3-4b-base-instruct-gguf and mradermacher/llm-surgery-dark-arts-gpt-oss-60b-96a12-i1-gguf: downloads, license, context length, tasks, and benchmarks.

janhq/jan-v3-4b-base-instruct-gguf

janhq · text-generation

# Jan-v3-4B-base-instruct: a 4B baseline model for fine-tuning ![GitHub](https://github.com/janhq/jan) ![License](https://opensource.org/licenses/Apache-2.0) ![Jan App](https://jan.ai/) !image

mradermacher/llm-surgery-dark-arts-gpt-oss-60b-96a12-i1-gguf

mradermacher · —

## About weighted/imatrix quants of https://huggingface.co/khoinguyenbk/llm-surgery-dark-arts-gpt-oss-60b-96a12 ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/llm-surgery-…

Side-by-side Specifications

	janhq/jan-v3-4b-base-instruct-gguf	mradermacher/llm-surgery-dark-arts-gpt-oss-60b-96a12-i1-gguf
Author	janhq	mradermacher
Pipeline Task	text-generation	—
Library	transformers	transformers
Downloads	120,417	26,608
Likes	52	1
License	Unknown	Unknown
Context Length	—	—
Created	2026-01-20	2026-03-19
Last Modified	2026-01-28	2026-03-21
Tags	transformersggufcodetext-generationenbase_model:janhq/Jan-v3-4B-base-instructbase_model:quantized:janhq/Jan-v3-4B-base-instructlicense:apache-2.0endpoints_compatibleregion:us	transformersggufvllmmoegpt-osssilent-initfinetunablereasoningmxfp4expert-expansion

View full details: janhq/jan-v3-4b-base-instruct-gguf · mradermacher/llm-surgery-dark-arts-gpt-oss-60b-96a12-i1-gguf