Step 3.5 Flash needs about 133.5 GB of memory at Q4_K (a 118.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds.
Step 3.5 Flash – a sparse Mixture of Experts LLM with 256K context
Step 3.5 Flash is a 197‑billion‑parameter model built on a step35 architecture. It uses a sparse MoE design that activates only 11B parameters per token, enabling efficient reasoning and agentic tasks. The model supports a 262144‑token context window and is released under the Apache‑2.0 license.
Good at
- Deep reasoning with high throughput
- Agentic task execution
- Long‑context handling
Limits
- Requires high‑end consumer hardware for local deployment
- Large memory footprint – 133.5 GB at 8k context
- No vision support
Best for
- Complex coding assistants
- Long‑form reasoning applications
- Agentic workflow automation
Who it’s for. Developers and researchers needing a powerful open‑source foundation model for reasoning, coding, and agentic tasks. The model is suitable for local deployment on high‑end consumer hardware and supports large context windows.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 118.7 GB | 133.5 GB | Too big | Get file → |
The available Q4_K quant is 118.71 GB. It requires approximately 133.5 GB of VRAM at an 8k context length. For users with less VRAM, a higher‑quantization level would be necessary, but no other quants are listed.
What GPU do you need for Step 3.5 Flash?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Step 3.5 Flash quant should you choose?
Q4_K (118.7 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Step 3.5 Flash
How much VRAM does Step 3.5 Flash need?
About 133.5 GB at Q4_K with an 8K context window. That is the 118.7 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 Step 3.5 Flash on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 133.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Step 3.5 Flash GGUF?
It depends on the quant: Q4_K is 118.7 GB.
What context length does Step 3.5 Flash support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download Step 3.5 Flash GGUF?
The files are on Hugging Face in the ggml-org/Step-3.5-Flash-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Step 3.5 Flash 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 Step 3.5 Flash on 8 GB VRAM?
No. The Q4_K quant requires about 133.5 GB of VRAM at 8k context, far exceeding 8 GB.
Does Step 3.5 Flash support vision tasks?
No, the model does not include vision capabilities.