TH

j a r v i s thinking

ThinkingGGUF by NeonFartUpdated 2026-10-02
Download on Hugging Face
Parameters3.09B
Context125K
Layers36
Architectureqwen2vl
Smallest quant1.9 GB
Quick answer

j a r v i s thinking needs about 2.7 GB of memory at its main file (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.

j a r v i s thinking – a 3.09B Qwen2VL model with reasoning and vision

j a r v i s thinking is a 3.09B parameter Qwen2VL model. It supports reasoning and vision tasks. The model is released under the apache-2.0 license.

Good at

  • reasoning
  • vision
  • mixed text‑image queries

Limits

  • requires ~2.7GB VRAM at 8k context
  • only one quant available
  • no other language support listed

Best for

  • image‑based reasoning
  • text‑image question answering
  • interactive visual assistants

Who it’s for. Developers and researchers who need a compact model that can handle both text and image inputs. The model is suitable for applications requiring reasoning over visual content.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.9 GB 2.7 GB
Fits Get file →

The only available quant is 1.93GB. It needs about 2.7GB of VRAM at 8k context. For 8GB VRAM, this quant fits comfortably. No other quant options are provided.

What GPU do you need for j a r v i s thinking?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is the main file (1.9 GB file, about 2.7 GB in use).

Specifications

Architecture from the GGUF header

Architectureqwen2vl
Parameters3.09B
Layers36
Trained context128,000 tokens
KV cache (fp16)36 KB per token

Source

Quantized byNeonFart
FamilyThinking
Licenseapache-2.0
Downloads (HF)679
Last updated2026-10-02

Frequently asked questions about j a r v i s thinking

How much VRAM does j a r v i s thinking need?

About 2.7 GB at its main file with an 8K context window. That is the 1.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run j a r v i s thinking on an 8 GB GPU?

Yes, with the smaller files: the 1.9 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of j a r v i s thinking GGUF?

It depends on the quant: file is 1.9 GB.

What context length does j a r v i s thinking support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.

Where can I download j a r v i s thinking GGUF?

The files are on Hugging Face in the NeonFart/j-a-r-v-i-s-thinking repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does j a r v i s thinking use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run j a r v i s thinking on 8 GB VRAM?

Yes, the 1.93GB quant requires about 2.7GB VRAM at 8k context, which fits within 8GB.

Does the model support vision tasks?

Yes, it has detected vision ability and is based on the Qwen2VL architecture.

What license does the model use?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More Thinking models

All Thinking →

Other tiny models

All tiny models →