Qwen3.8-Flash-Next GSQ-RCO needs about 91.6 GB of memory at IQ3_S (a 90.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
Qwen3.8-Flash-Next GSQ-RCO, a 132B MoE model with vision and coding abilities
Qwen3.8-Flash-Next GSQ-RCO is a 132‑billion‑parameter mixture‑of‑experts model with 512 routed experts per layer. It supports coding, reasoning, tools, and vision, and is quantized with GSQ‑RCO to a 90.31‑GB GGUF file. The model runs unmodified in llama.cpp, Ollama, and LM Studio.
Good at
- Coding and code generation
- Multimodal vision tasks
- Reasoning and tool use
Limits
- Requires ~91.6 GB VRAM at 8 k context
- No official license, community derivative
- No native vision support in some runtimes
Best for
- Developers needing a large multimodal LLM
- Researchers testing MoE architectures
- Code‑centric applications with vision input
Who it’s for. This model is suited for users who need a large, multimodal language model with strong coding capabilities. It is ideal for developers and researchers working on code generation, multimodal inference, and advanced reasoning tasks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_S | 90.3 GB (2 parts) | 91.6 GB | Too big | Get file → |
The only available quantization is IQ3_S, producing a 90.31‑GB GGUF file. It requires approximately 91.6 GB VRAM at 8 k context. For lower memory budgets, no alternative quant is provided in the file list.
What GPU do you need for Qwen3.8-Flash-Next GSQ-RCO?
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: 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 Qwen3.8-Flash-Next GSQ-RCO quant should you choose?
IQ3_S (90.3 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Qwen3.8-Flash-Next GSQ-RCO
How much VRAM does Qwen3.8-Flash-Next GSQ-RCO need?
About 91.6 GB at IQ3_S with an 8K context window. That is the 90.3 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 GSQ-RCO on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 91.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3.8-Flash-Next GSQ-RCO GGUF?
It depends on the quant: IQ3_S is 90.3 GB.
What context length does Qwen3.8-Flash-Next GSQ-RCO 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 3.2 GB at 32K.
Where can I download Qwen3.8-Flash-Next GSQ-RCO GGUF?
The files are on Hugging Face in the qmnvp/Qwen3.8-Flash-Next-GSQ-RCO-Coder-320-PLE8-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 GSQ-RCO 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 GSQ-RCO on 8 GB VRAM?
No, the model requires about 91.6 GB VRAM at 8 k context.
Does the model support vision tasks?
Yes, it includes a vision projector for multimodal use.
Is there a smaller quantized version available?
Only the IQ3_S quantization is provided; no other sizes are listed.