needle3
needle3 is an open-weights language model from Cactus-Compute, released September 16, 2026. The context window is 8K tokens.
Check it against your own PC →
Lab
Cactus-Compute
Released
September 16, 2026
Weights
Open apache-2.0
Parameters
–
Context
8K
Price / M tokens
–
Epoch ECI
not yet rated
Can you run needle3 locally?
Even with 32 GB of VRAM and 32 GB of RAM it is too large to run at a usable speed on a single consumer GPU. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Size unknown | – | – | – | – |
| 8 GB VRAM | Size unknown | – | – | – | – |
| 12 GB VRAM | Size unknown | – | – | – | – |
| 16 GB VRAM | Size unknown | – | – | – | – |
| 24 GB VRAM | Size unknown | – | – | – | – |
| 32 GB VRAM | Size unknown | – | – | – | – |
Parameter count unknown. The weights may not be on Hugging Face yet.
Ready-made quantizations on Hugging Face: webmp3/Sakura-Needle3-ONNX · gigglr/needle3-onnx · mrfakename/needle3-ONNX
Benchmark results
Epoch AI has not published results for needle3 yet. New models are usually evaluated within days to weeks.
Links
Hugging Face: Cactus-Compute/needle3