Swift 1.5 Qwen3.8 27B Badger Mixed needs about 21.6 GB of memory at its main file (a 18.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 0.0 GB to 19.5 GB (Q5_K_M).
Swift 1.5 Qwen3.8 27B Badger Mixed – a fast, reasoning‑efficient local LLM
Swift 1.5 Qwen3.8 27B Badger Mixed is a mixed‑precision build of Swift 1.5, optimized for local agents on Apple Silicon. It retains full 262,144‑token context and vision support, and runs through llama.cpp with Metal acceleration.
Good at
- Fast local inference on Apple Silicon
- Large context window
- Vision‑enabled reasoning
Limits
- Requires 48 GB VRAM for full performance
- Large memory footprint (≈22 GB at 8 k context)
- License is other, not open source
Best for
- Local agent development
- Coding assistance
- Vision‑based task automation
Who it’s for. Developers and researchers who need a high‑performance, local LLM with extended context and vision capabilities, and who can run it on Apple Silicon with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 18.9 GB | 21.6 GB | Too big | Get file → | |
| Q5_K_M | 19.5 GB | 22.4 GB | Too big | Get file → |
For 8 GB VRAM use the 0.01 GB unknown quant (≈0.5 GB memory). For 20 GB VRAM use the 18.87 GB unknown quant (≈21.6 GB memory). For 48 GB VRAM use the Q5_K_M quant (≈22.4 GB memory).
What GPU do you need for Swift 1.5 Qwen3.8 27B Badger Mixed?
These figures add the file size, an fp16 KV cache at an 8K context window 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 the main file (0.0 GB file, about 0.5 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.5 GB file, about 22.4 GB in use).
Which Swift 1.5 Qwen3.8 27B Badger Mixed quant should you choose?
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Swift 1.5 Qwen3.8 27B Badger Mixed
How much VRAM does Swift 1.5 Qwen3.8 27B Badger Mixed need?
About 21.6 GB at its main file with an 8K context window. That is the 18.9 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 Swift 1.5 Qwen3.8 27B Badger Mixed on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 0.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Swift 1.5 Qwen3.8 27B Badger Mixed GGUF?
It depends on the quant: file is 0.0 GB, file is 18.9 GB, Q5_K_M is 19.5 GB.
Where can I download Swift 1.5 Qwen3.8 27B Badger Mixed GGUF?
The files are on Hugging Face in the CleverBadger/Swift-1.5-Qwen3.8-27B-Badger-Mixed-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 Swift 1.5 Qwen3.8 27B Badger Mixed 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 Swift 1.5 Qwen3.8 27B Badger Mixed on a 48 GB MacBook Pro?
Yes, it is designed for 48 GB Apple Silicon and runs with Metal acceleration.
What is the memory requirement for the Q5_K_M quant?
Approximately 22.4 GB at an 8 k context length.
Does the model support vision tasks?
Yes, the Badger Mixed build retains vision support.