Mach 1 Additive 35B Multimodal needs about 9.0 GB of memory at its main file (a 7.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Mach 1 Additive 35B Multimodal – 4.19B parameter model with vision capability
Mach 1 Additive 35B Multimodal is a 4.19B parameter multimodal model built on the Mach-1 architecture. It supports vision tasks and is available as a GGUF file for local inference on consumer hardware.
Good at
- Vision inference
- Multimodal text and image tasks
- Local deployment with llama.cpp-mach1
Limits
- Requires Mach-1 fork of llama.cpp
- No other quantizations available
- Large memory requirement
Best for
- Local image captioning
- Multimodal chat on consumer GPUs
- Vision‑enabled LLM applications
Who it’s for. Developers needing a multimodal model that can run locally on NVIDIA or AMD/Intel GPUs using the llama.cpp-mach1 fork. Suitable for projects that require vision input without cloud inference.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 7.9 GB | 9.0 GB | Too big | Get file → |
The only available quantization is the default GGUF file (quant: unknown). It has a file size of 7.87 GB and requires approximately 9 GB of VRAM at an 8 k context length. This estimate is approximate.
What GPU do you need for Mach 1 Additive 35B Multimodal?
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: the best quant that fits is the main file (7.9 GB file, about 9.0 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Mach 1 Additive 35B Multimodal
How much VRAM does Mach 1 Additive 35B Multimodal need?
About 9.0 GB at its main file with an 8K context window. That is the 7.9 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 Mach 1 Additive 35B Multimodal on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Mach 1 Additive 35B Multimodal GGUF?
It depends on the quant: file is 7.9 GB.
What context length does Mach 1 Additive 35B Multimodal support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.
Where can I download Mach 1 Additive 35B Multimodal GGUF?
The files are on Hugging Face in the SyzygyResearch/Mach-1-Additive-35B-Multimodal-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 1 Additive 35B Multimodal 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 1 Additive 35B Multimodal on 8 GB VRAM?
The model requires about 9 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does the model support vision tasks?
Yes, the model has detected vision capability.
What license does the model use?
The model is licensed under apache-2.0.