Swift1.5 Qwen3.8 Flash Next Mixed Quant needs about 84.6 GB of memory at BF16 (a 83.3 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.
Swift1.5 Qwen3.8 Flash Next Mixed Quant – a 129B Qwen4exp model with vision support
Swift1.5 Qwen3.8 Flash Next Mixed Quant is a 129‑billion‑parameter Qwen4exp model. It includes vision capabilities and is released as a BF16 GGUF file. The model is a mixture of experts and was trained with a context length of 262144 tokens.
Good at
- Vision tasks
- Large context reasoning
- Efficient token usage
Limits
- No explicit license details
- Requires BF16 quant only
- Large model size
Best for
- Vision‑enabled LLM inference
- Long‑form content generation
- Agent‑style reasoning
Who it’s for. Developers needing a large, vision‑capable Qwen model for inference on systems that support BF16. The model is suitable for research or production environments where the 83.27 GB file can be accommodated.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 83.3 GB (3 parts) | 84.6 GB | Too big | Get file → |
For systems with limited memory, the BF16 quant is the only available variant. The file is 83.27 GB and requires roughly 84.6 GB of VRAM at 8k context. Use a system with at least 90 GB VRAM to run safely.
What GPU do you need for Swift1.5 Qwen3.8 Flash Next Mixed Quant?
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 Swift1.5 Qwen3.8 Flash Next Mixed Quant quant should you choose?
BF16 (83.3 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Swift1.5 Qwen3.8 Flash Next Mixed Quant
How much VRAM does Swift1.5 Qwen3.8 Flash Next Mixed Quant need?
About 84.6 GB at BF16 with an 8K context window. That is the 83.3 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 Swift1.5 Qwen3.8 Flash Next Mixed Quant on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 84.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Swift1.5 Qwen3.8 Flash Next Mixed Quant GGUF?
It depends on the quant: BF16 is 83.3 GB.
What context length does Swift1.5 Qwen3.8 Flash Next Mixed Quant 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 Swift1.5 Qwen3.8 Flash Next Mixed Quant GGUF?
The files are on Hugging Face in the Baekpica/Swift1.5-Qwen3.8-Flash-Next-Mixed-Quant-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 Swift1.5 Qwen3.8 Flash Next Mixed Quant 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 Swift1.5 Qwen3.8 Flash Next on 8 GB VRAM?
No. The BF16 file requires about 84.6 GB of VRAM at 8k context, far exceeding 8 GB.
Does this model support vision?
Yes, the model has detected vision abilities.
What quantization is available?
Only BF16 is provided in the GGUF file list.