Qwen3.8-Flash-Next GSQ-RCO Coder needs about 60.0 GB of memory at IQ1_M (a 58.7 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 Coder – 117B parameter code‑focused model
This 117B‑parameter model is a compressed, code‑centric version of Qwen3.8‑Flash‑Next. Half of the routed experts are removed and the remaining weights are stored at 3.5 bpw, yielding a 58.65 GB GGUF file. It retains multimodal vision support and is uncensored.
Good at
- Code generation
- Agentic tool use
- Vision tasks
Limits
- Requires 58.65 GB of VRAM or RAM for full residency
- No image‑to‑text generation beyond basic vision
- License is Apache‑2.0
Best for
- Developers needing large‑scale code models
- Agents that combine coding and vision
- Research on expert pruning
Who it’s for. Engineers and researchers who need a large, code‑focused model with vision capability. The model is suitable for environments with sufficient memory to host the full 58.65 GB file.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_M | 58.7 GB (2 parts) | 60.0 GB | Too big | Get file → |
For 8 GB VRAM, use the 58.65 GB IQ1_M shard; the resident working set is approximately 60 GB at 8 k context, so this requires a 32 GB or larger accelerator. For 16 GB VRAM, the same shard can be loaded with off‑loading of the n‑gram shard. No other quants are available.
What GPU do you need for Qwen3.8-Flash-Next GSQ-RCO Coder?
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 Coder quant should you choose?
IQ1_M (58.7 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Qwen3.8-Flash-Next GSQ-RCO Coder
How much VRAM does Qwen3.8-Flash-Next GSQ-RCO Coder need?
About 60.0 GB at IQ1_M with an 8K context window. That is the 58.7 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 Qwen3.8-Flash-Next GSQ-RCO Coder on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 60.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3.8-Flash-Next GSQ-RCO Coder GGUF?
It depends on the quant: IQ1_M is 58.7 GB.
What context length does Qwen3.8-Flash-Next GSQ-RCO Coder 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 Coder GGUF?
The files are on Hugging Face in the DatKurai/Qwen3.8-Flash-Next-GSQ-RCO-Coder-Uncen-IQ1_M-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 Coder 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?
No. The model requires about 60 GB of VRAM for a full 8 k context run, so a 32 GB or larger accelerator is needed.
Does this model support vision?
Yes, it retains basic vision capability as part of the Qwen family.
What license applies?
The model is released under the Apache‑2.0 license.