Qwen3.8 Flash Next FLE needs about 72.9 GB of memory at IQ2_M (a 71.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 1.5 GB (IQ4_NL) to 88.9 GB (IQ3_M). Longer context needs more: at 32K tokens the KV cache alone adds about 3.3 GB.
Qwen3.8 Flash Next FLE – 177B hybrid‑MoE LLM in GGUF format
Qwen3.8 Flash Next FLE is a 177‑billion‑parameter hybrid‑Mixture‑of‑Experts model based on the Qwen4 architecture. It supports a 262,144‑token context window and is distributed as several GGUF quantizations for llama.cpp. The model is released under an other license.
Good at
- Long‑context reasoning
- Hybrid attention with QSA
- Efficient MoE scaling
Limits
- No vision support
- Requires FLE engine for full MoE inference
- Large VRAM needed for higher‑bit quantizations
Best for
- Chatbots needing 256‑k token context
- Agentic workflows with long prompts
- Research on hybrid attention mechanisms
Who it’s for. Developers building local LLM deployments that need very long context and efficient MoE inference. The model is suited for users who can run llama.cpp with the FLE fork and have sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_NL | 1.5 GB | 2.9 GB | Fits | Get file → | |
| IQ2_M | 71.6 GB (2 parts) | 72.9 GB | Too big | Get file → | |
| IQ3_XXS | 79.5 GB (2 parts) | 80.8 GB | Too big | Get file → | |
| IQ3_M | 88.9 GB (2 parts) | 90.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ4_NL (file size 1.53 GB, estimated 2.9 GB memory at 8 k context). If 16 GB VRAM is available, IQ2_M (71.62 GB file, ~72.9 GB memory) or IQ3_XXS (79.48 GB file, ~80.8 GB memory) can be considered, though they require system RAM for sharding. IQ3_M (88.87 GB file, ~90.2 GB memory) is best for high‑end GPUs with >90 GB VRAM.
What GPU do you need for Qwen3.8 Flash Next FLE?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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: the best quant that fits is IQ4_NL (1.5 GB file, about 2.9 GB in use).
- 6 GB VRAM: the best quant that fits is IQ4_NL (1.5 GB file, about 2.9 GB in use).
- 8 GB VRAM: the best quant that fits is IQ4_NL (1.5 GB file, about 2.9 GB in use).
- 12 GB VRAM: the best quant that fits is IQ4_NL (1.5 GB file, about 2.9 GB in use).
- 16 GB VRAM: the best quant that fits is IQ4_NL (1.5 GB file, about 2.9 GB in use).
- 24 GB VRAM: the best quant that fits is IQ4_NL (1.5 GB file, about 2.9 GB in use).
- 32 GB VRAM: the best quant that fits is IQ4_NL (1.5 GB file, about 2.9 GB in use).
- 48 GB VRAM: the best quant that fits is IQ4_NL (1.5 GB file, about 2.9 GB in use).
Which Qwen3.8 Flash Next FLE quant should you choose?
IQ2_M (71.6 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ4_NL at 1.5 GB, with the quality trade-offs that come with fewer bits. 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 Qwen3.8 Flash Next FLE
How much VRAM does Qwen3.8 Flash Next FLE need?
About 72.9 GB at IQ2_M with an 8K context window. That is the 71.6 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 Qwen3.8 Flash Next FLE on an 8 GB GPU?
Yes, with IQ4_NL: the 1.5 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.8 Flash Next FLE GGUF?
It depends on the quant: IQ4_NL is 1.5 GB, IQ2_M is 71.6 GB, IQ3_XXS is 79.5 GB, IQ3_M is 88.9 GB.
What context length does Qwen3.8 Flash Next FLE support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.3 GB at 32K.
Where can I download Qwen3.8 Flash Next FLE GGUF?
The files are on Hugging Face in the sirfyyn/Qwen3.8-Flash-Next-FLE-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 Qwen3.8 Flash Next FLE use?
Hugging Face lists the license as other. 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 Qwen3.8 Flash Next FLE on 8 GB VRAM?
Yes, using the IQ4_NL quantization which requires about 2.9 GB VRAM at 8 k context.
Does the model support vision tasks?
No, the model has no vision capabilities.
What engine is needed for full inference?
The FLE fork of llama.cpp is required to run the hybrid MoE efficiently.