QW

starvla qwen25 pi bridge bf16

QwenGGUF by robotcppUpdated 2026-08-25
Download on Hugging Face
Parameters3.4B
Context125K
Layers—
Architecturestarvla-policy
Smallest quant3.9 GB
Quick answer

starvla qwen25 pi bridge bf16 needs about 4.9 GB of memory at its main file (a 3.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 3.9 GB to 6.8 GB (BF16).

starvla qwen25 pi bridge bf16 is a 3.4B-parameter Qwen model in GGUF format, quantized by robotcpp. Its trained context length is 125K tokens. The repository has 2 quant files, from 3.9 GB to 6.8 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—3.9 GB 4.9 GB
Fits Get file →
BF166.8 GB 8.1 GB
Too big Get file →

What GPU do you need for starvla qwen25 pi bridge bf16?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is the main file (3.9 GB file, about 4.9 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (3.9 GB file, about 4.9 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (6.8 GB file, about 8.1 GB in use).

Specifications

Architecture from the GGUF header

Architecturestarvla-policy
Parameters3.4B
Trained context128,000 tokens

Source

Quantized byrobotcpp
FamilyQwen
Downloads (HF)41
Last updated2026-08-25

Frequently asked questions about starvla qwen25 pi bridge bf16

How much VRAM does starvla qwen25 pi bridge bf16 need?

About 4.9 GB at its main file with an 8K context window. That is the 3.9 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 starvla qwen25 pi bridge bf16 on an 8 GB GPU?

Yes, with the smaller files: the 3.9 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of starvla qwen25 pi bridge bf16 GGUF?

It depends on the quant: file is 3.9 GB, BF16 is 6.8 GB.

What context length does starvla qwen25 pi bridge bf16 support?

The GGUF header lists a trained context length of 128,000 tokens (125K).

Where can I download starvla qwen25 pi bridge bf16 GGUF?

The files are on Hugging Face in the robotcpp/starvla-qwen25-pi-bridge-bf16 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from robotcpp

All by robotcpp →

More Qwen models

All Qwen →

Other tiny models

All tiny models →