TimeLens2-4B
MCG-NJUapache-2.0textvisionvideo

TimeLens2-4B

Updated Nov 21, 2026
Parameters
4.4B
Context
262,144
License
apache-2.0
Q4 GGUF
2.72 GB
Updated
Nov 21, 2026

Q4 GGUF download: mradermacher/TimeLens2-4B-GGUF - 2.72 GB on disk, read 2026-11-14. VRAM figures above are estimates; this is the actual file size.

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Runs on your 24 GB - best at FP16
4 of 4 quantizations fit TimeLens2-4B with real runtime overhead.
Q4_K_M
3 GB
Q5_K_M
3 GB
Q8_0
5 GB
FP16
9 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve MCG-NJU/TimeLens2-4B

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

TimeLens2-4B is an open-weight video understanding model published by MCG-NJU on Hugging Face in July 2026, with 4.4B parameters under the apache-2.0 license. It is built on Qwen/Qwen3-VL-4B-Instruct.

Among the 16 video understanding models in this directory it ranks 14th by monthly Hugging Face downloads, and 14 of the others are larger.

HardwareLink to this section

Unquantized FP16 weights take about 9 GB; 8-bit brings that to ~5 GB and 4-bit (Q4_K_M) to ~3 GB, before activations and any context or image buffers. A 12 GB consumer card holds it at 4-bit; FP16 needs a 24 GB card such as an RTX 4090. Check exact numbers for your card with the VRAM calculator.

Similar video understanding modelsLink to this section

PopularityLink to this section

TimeLens2-4B was downloaded 1,076 times on Hugging Face in the last month (4,832 all-time) and has 14 likes.

Run it locallyLink to this section

Weights and usage instructions are on the MCG-NJU/TimeLens2-4B model card; it loads with Hugging Face Transformers.

Local runtimes that fit this model:

  • vllm - high-throughput serving on NVIDIA GPUs
  • transformers - the reference Python library most model cards target

PaperLink to this section

Frequently asked

Quick answers to common questions

How much VRAM does TimeLens2-4B need?

TimeLens2-4B with 4.4B parameters needs approximately 3 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is TimeLens2-4B better than other MCG-NJU models?

TimeLens2-4B has 4.4B parameters with 262,144 context - a strong choice for video-understanding, vision.

What license is TimeLens2-4B under?

TimeLens2-4B is released under the apache-2.0 license, making it suitable for most commercial and personal projects.

What hardware runs TimeLens2-4B well?

With 4.4B parameters, TimeLens2-4B requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.

What is the best quantization for TimeLens2-4B?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~3 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

How long can TimeLens2-4B's context window handle?

TimeLens2-4B supports a 262,144-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.

What models compete with TimeLens2-4B?

TimeLens2-4B competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec