Step 3.5 Flash needs about 133.3 GB of memory at Q4_K_M (a 118.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 10 quants, from 71.8 GB (Q2_K) to 161.7 GB (Q6_K).
Step 3.5 Flash – a sparse Mixture of Experts model with 256K context
Step 3.5 Flash is a 197 billion‑parameter model built on a sparse Mixture of Experts architecture. It activates only 11 billion parameters per token, enabling efficient reasoning and agentic tasks. The model supports a 262 144‑token context window and is released under Apache‑2.0.
Good at
- Deep reasoning and multi‑step logic
- Agentic task execution
- Long‑context handling up to 256K tokens
Limits
- Requires large VRAM for higher‑quality quants
- No vision support
- Mixture of Experts may increase latency
Best for
- Complex coding assistants
- Long‑form document analysis
- AI agent workflows
Who it’s for. Developers and researchers needing a high‑capacity, open‑source foundation model for reasoning and agentic applications. The model is suitable for local deployment on systems with sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 71.8 GB | 80.9 GB | Too big | Get file → | |
| Q3_K_S | 85.0 GB | 95.7 GB | Too big | Get file → | |
| Q3_K_M | 93.8 GB | 105.6 GB | Too big | Get file → | |
| Q3_K_L | 102.0 GB | 114.8 GB | Too big | Get file → | |
| IQ4_XS | 105.5 GB | 118.6 GB | Too big | Get file → | |
| Q4_K_S | 111.5 GB | 125.4 GB | Too big | Get file → | |
| Q4_K_M | 118.6 GB | 133.3 GB | Too big | Get file → | |
| Q5_K_S | 135.6 GB | 152.4 GB | Too big | Get file → | |
| Q5_K_M | 139.5 GB | 156.7 GB | Too big | Get file → | |
| Q6_K | 161.7 GB | 181.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (71.81 GB, ~80.9 GB memory at 8k context). For 16 GB VRAM, Q3_K_S (85.02 GB, ~95.7 GB memory) or Q3_K_M (93.8 GB, ~105.6 GB). For 24 GB VRAM, Q4_K_S (111.5 GB, ~125.4 GB) or Q4_K_M (118.58 GB, ~133.3 GB). Memory estimates are approximate.
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_M is the usual starting point for Step 3.5 Flash: it balances file size and quality well. Here it is a 118.6 GB file.
If memory is tight, the smallest file is Q2_K at 71.8 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
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 133.3 GB at Q4_K_M with an 8K context window. That is the 118.6 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 80.9 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: Q2_K is 71.8 GB, Q3_K_S is 85.0 GB, Q3_K_M is 93.8 GB, Q3_K_L is 102.0 GB, IQ4_XS is 105.5 GB, Q4_K_S is 111.5 GB and 4 more.
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 mradermacher/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 a GPU with 8 GB VRAM?
Use the Q2_K quant, which requires about 80.9 GB of memory at 8k context. It will not fit on 8 GB VRAM, so a lower‑quality quant or a larger GPU is needed.
Does Step 3.5 Flash support vision tasks?
No, the model has no vision capabilities.
What license applies to Step 3.5 Flash?
The model is released under the Apache‑2.0 license.