Mach 2 Additive Medium needs about 131.4 GB of memory at its main file (a 130.1 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.
Mach 2 Additive Medium – a 65.6B Qwen4exp model with vision support
Mach 2 Additive Medium is a 65.6B parameter Qwen4exp model quantized to 1.70 bits per weight. It includes a 0.9 GB vision tower and a 102.4 GB n‑gram embedding table. The GGUF file is 130.08 GB and requires the Mach‑1 fork of llama.cpp.
Good at
- Large context handling up to 262144 tokens
- Vision and text combined inference
- High‑capacity language modeling
Limits
- Requires >131 GB VRAM
- No support for mainline llama.cpp
- License is Apache‑2.0
Best for
- Research on long‑form generation
- Vision‑enabled multimodal tasks
- Benchmarking large‑scale LLMs
Who it’s for. Researchers and developers needing a large Qwen4exp model with integrated vision. The model is suitable for environments that can accommodate its memory footprint and use the Mach‑1 fork of llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 130.1 GB | 131.4 GB | Too big | Get file → |
The only available GGUF file is 130.08 GB and needs about 131.4 GB of VRAM at 8 k context. This estimate is approximate. No other quantizations are provided.
What GPU do you need for Mach 2 Additive Medium?
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.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Mach 2 Additive Medium
How much VRAM does Mach 2 Additive Medium need?
About 131.4 GB at its main file with an 8K context window. That is the 130.1 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 Mach 2 Additive Medium on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 131.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Mach 2 Additive Medium GGUF?
It depends on the quant: file is 130.1 GB.
What context length does Mach 2 Additive Medium 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 Mach 2 Additive Medium GGUF?
The files are on Hugging Face in the SyzygyResearch/Mach-2-Additive-Medium-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 Mach 2 Additive Medium 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 Mach 2 Additive Medium on 8 GB VRAM?
No. The model requires approximately 131.4 GB of VRAM at 8 k context.
Does the model support vision input?
Yes. It includes a 0.9 GB vision tower that can be loaded directly.
What license applies to this model?
The model is released under the Apache‑2.0 license.