ThinkingCap Qwen3.8 Flash-Next needs about 114.5 GB of memory at Q4_K_M (a 113.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 95.5 GB (IQ4_XS) to 359.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.3 GB.
ThinkingCap Qwen3.8 Flash-Next – a 180B mixture‑of‑experts model with vision and reasoning
ThinkingCap Qwen3.8 Flash-Next is a 180B Qwen4exp model fine‑tuned for efficient reasoning and image input. It reduces thinking tokens by 38.5% on average while maintaining high accuracy. The model is available in several GGUF quantizations for local deployment.
Good at
- Efficient reasoning with fewer tokens
- Vision input support
- Multi‑turn agentic tasks
Limits
- Requires large VRAM for high‑quality quants
- No native vision support in some runtimes
- License is other, not open source
Best for
- Local inference with limited GPU memory
- Interactive image‑based Q&A
- Agentic workflows needing reduced token counts
Who it’s for. Developers and researchers who need a high‑capacity Qwen model that is more efficient in token usage and supports vision. The model is suitable for local deployment via llama.cpp, Ollama, or LM Studio.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 95.5 GB (8 parts) | 96.9 GB | Too big | Get file → | |
| Q4_K_M | 113.2 GB (8 parts) | 114.5 GB | Too big | Get file → | |
| Q6_K | 171.9 GB (8 parts) | 173.2 GB | Too big | Get file → | |
| Q8_0 | 191.0 GB (8 parts) | 192.3 GB | Too big | Get file → | |
| BF16 | 359.2 GB (8 parts) | 360.6 GB | Too big | Get file → |
For 8 GB VRAM, use IQ4_XS (file size 95.53 GB, memory 96.9 GB at 8k context). For 16 GB VRAM, Q4_K_M (113.19 GB, 114.5 GB). For 32 GB VRAM, Q6_K (171.9 GB, 173.2 GB). BF16 and Q8_0 require more than 32 GB and are not recommended for typical local setups.
What GPU do you need for ThinkingCap Qwen3.8 Flash-Next?
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 ThinkingCap Qwen3.8 Flash-Next quant should you choose?
Q4_K_M is the usual starting point for ThinkingCap Qwen3.8 Flash-Next: it balances file size and quality well. Here it is a 113.2 GB file.
The Q8_0 file is 191.0 GB, about 1.7 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 IQ4_XS at 95.5 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
Frequently asked questions about ThinkingCap Qwen3.8 Flash-Next
How much VRAM does ThinkingCap Qwen3.8 Flash-Next need?
About 114.5 GB at Q4_K_M with an 8K context window. That is the 113.2 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 ThinkingCap Qwen3.8 Flash-Next on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 96.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of ThinkingCap Qwen3.8 Flash-Next GGUF?
It depends on the quant: IQ4_XS is 95.5 GB, Q4_K_M is 113.2 GB, Q6_K is 171.9 GB, Q8_0 is 191.0 GB, BF16 is 359.2 GB.
What context length does ThinkingCap Qwen3.8 Flash-Next 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 ThinkingCap Qwen3.8 Flash-Next GGUF?
The files are on Hugging Face in the bottlecapai/ThinkingCap-Qwen3.8-Flash-Next-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 ThinkingCap Qwen3.8 Flash-Next 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 on 8 GB VRAM?
Only the IQ4_XS quantization is feasible, but it still requires about 96.9 GB of VRAM at 8k context, so 8 GB is insufficient.
Does the model support image input?
Yes, the base model includes vision capability, but some runtimes may need additional configuration.
What is the recommended quant for best quality?
Q4_K_M offers a good balance between size and quality for most local setups.