Step 3.5 Flash REAP 128B A11B needs about 82.1 GB of memory at Q4_K_M (a 72.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 11 quants, from 44.2 GB (Q2_K) to 128.6 GB (Q8_0).
Step 3.5 Flash REAP 128B A11B – 121B parameter LLM with mixture of experts
Step 3.5 Flash REAP 128B A11B is a 121B parameter language model with 11B active parameters. It supports coding, reasoning, and tools. The model is trained on 262144 context tokens and is licensed under apache-2.0.
Good at
- Coding tasks
- Logical reasoning
- Tool integration
Limits
- No vision support
- Requires large VRAM for high‑quality quants
- Mixture of experts limits context length
Best for
- Local inference on high‑end GPUs
- Developers needing coding assistance
- Researchers exploring MoE models
Who it’s for. This model is suited for developers and researchers who require a large, locally deployable language model with strong coding and reasoning capabilities. It is ideal for environments where privacy and offline inference are priorities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 44.2 GB | 50.0 GB | Too big | Get file → | |
| Q3_K_S | 52.3 GB | 59.1 GB | Too big | Get file → | |
| Q3_K_M | 57.7 GB | 65.1 GB | Too big | Get file → | |
| Q3_K_L | 62.8 GB | 70.8 GB | Too big | Get file → | |
| IQ4_XS | 64.9 GB | 73.1 GB | Too big | Get file → | |
| Q4_K_S | 68.5 GB | 77.3 GB | Too big | Get file → | |
| Q4_K_M | 72.8 GB | 82.1 GB | Too big | Get file → | |
| Q5_K_S | 83.3 GB | 93.8 GB | Too big | Get file → | |
| Q5_K_M | 85.7 GB | 96.5 GB | Too big | Get file → | |
| Q6_K | 99.3 GB | 111.8 GB | Too big | Get file → | |
| Q8_0 | 128.6 GB | 144.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (44.23 GB file, ~50 GB memory at 8k context). For 16 GB VRAM, Q3_K_S (52.3 GB file, ~59.1 GB memory) or Q4_K_S (68.54 GB file, ~77.3 GB memory). For 24 GB VRAM, Q5_K_M (85.67 GB file, ~96.5 GB memory) offers a balance between size and performance. Estimates are approximate.
What GPU do you need for Step 3.5 Flash REAP 128B A11B?
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 REAP 128B A11B quant should you choose?
Q4_K_M is the usual starting point for Step 3.5 Flash REAP 128B A11B: it balances file size and quality well. Here it is a 72.8 GB file.
The Q8_0 file is 128.6 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 44.2 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 REAP 128B A11B
How much VRAM does Step 3.5 Flash REAP 128B A11B need?
About 82.1 GB at Q4_K_M with an 8K context window. That is the 72.8 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 REAP 128B A11B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 50.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Step 3.5 Flash REAP 128B A11B GGUF?
It depends on the quant: Q2_K is 44.2 GB, Q3_K_S is 52.3 GB, Q3_K_M is 57.7 GB, Q3_K_L is 62.8 GB, IQ4_XS is 64.9 GB, Q4_K_S is 68.5 GB and 5 more.
What context length does Step 3.5 Flash REAP 128B A11B support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download Step 3.5 Flash REAP 128B A11B GGUF?
The files are on Hugging Face in the mradermacher/Step-3.5-Flash-REAP-128B-A11B-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 REAP 128B A11B 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 this model on 8 GB VRAM?
Use the Q2_K quant, which requires about 50 GB of VRAM at 8k context, so 8 GB VRAM is insufficient.
Does this model support vision tasks?
No, the model does not have vision capabilities.
What backend can I use for local inference?
Supported backends include vLLM, SGLang, Hugging Face Transformers, and llama.cpp.