NE

needle 8b

NeedleGGUF by KyrillosIshakUpdated 2026-08-05
Download on Hugging Face
Parameters8.19B
Context256K
Layers36
Architectureqwen3vl
Smallest quant8.7 GB
Quick answer

needle 8b needs about 10.4 GB of memory at Q8_0 (a 8.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Needle 8B – a Qwen3VL model with tools and vision support

Needle 8B is an 8.19B parameter Qwen3VL model. It supports tools and vision and was trained on a context of 262144 tokens. The model is available in a single Q8_0 quantized GGUF file.

Good at

  • Tools usage
  • Vision tasks
  • Large context handling

Limits

  • Requires 10.4 GB VRAM at 8k context
  • Only Q8_0 quant available
  • No license information

Best for

  • Tool‑assisted code generation
  • Image captioning
  • Long‑form reasoning

Who it’s for. Developers and researchers who need a compact 8B Qwen3VL model with integrated tools and vision capabilities. Suitable for experimentation and production workloads that can accommodate the memory requirements.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_08.7 GB (10 parts) 10.4 GB
Too big Get file →

The only available quant is Q8_0, 8.71 GB in size. It requires approximately 10.4 GB VRAM at 8k context. The file is split into 10 shards for easier loading.

What GPU do you need for needle 8b?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).

Which needle 8b quant should you choose?

Q8_0 (8.7 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3vl
Parameters8.19B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized byKyrillosIshak
FamilyNeedle
Downloads (HF)631
Last updated2026-08-05

Frequently asked questions about needle 8b

How much VRAM does needle 8b need?

About 10.4 GB at Q8_0 with an 8K context window. That is the 8.7 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 needle 8b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of needle 8b GGUF?

It depends on the quant: Q8_0 is 8.7 GB.

What context length does needle 8b support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download needle 8b GGUF?

The files are on Hugging Face in the KyrillosIshak/needle-8b-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run needle 8b on 8 GB VRAM?

No, it requires about 10.4 GB VRAM at 8k context.

Does it support vision?

Yes, it has vision capability.

What quantization is available?

Only Q8_0 is provided.

Similar models

Browse all →

Other small models

All small models →