Thomson 1.0 Small needs about 15.9 GB of memory at its main file (a 14.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Thomson 1.0 Small – a 34.7B MoE model with full 256K context
Thomson 1.0 Small is a 34.7B parameter Mixture‑of‑Experts model built on the qwen35moe architecture. It offers reasoning capabilities and supports a 262144 token context window. The model is released under the Apache‑2.0 license.
Good at
- Reasoning tasks
- Legal and tax domain queries
- Journalistic content generation
Limits
- No vision support
- Requires ~15.9 GB VRAM at 8 k context
- Large file size 14.75 GB
Best for
- Legal research assistants
- Tax compliance analysis
- Journalistic fact‑checking
Who it’s for. Developers and researchers needing a high‑capacity reasoning model for professional domains. The model is open‑weight and can be fine‑tuned or used as a foundation for specialized applications.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 14.8 GB | 15.9 GB | Too big | Get file → |
The only available GGUF file is 14.75 GB with an estimated 15.9 GB memory footprint at 8 k context. This is the recommended version for workstations with 24 GB VRAM or higher. Smaller VRAM setups cannot run this model without offloading or further quantization, which is not provided.
What GPU do you need for Thomson 1.0 Small?
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: the best quant that fits is the main file (14.8 GB file, about 15.9 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Thomson 1.0 Small
How much VRAM does Thomson 1.0 Small need?
About 15.9 GB at its main file with an 8K context window. That is the 14.8 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 Thomson 1.0 Small on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Thomson 1.0 Small GGUF?
It depends on the quant: file is 14.8 GB.
What context length does Thomson 1.0 Small 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 Thomson 1.0 Small GGUF?
The files are on Hugging Face in the IsValorum/Thomson-1.0-Small-APEX-I-MiniPlus-V2.1-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 Thomson 1.0 Small 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 Thomson 1.0 Small on 8 GB VRAM?
No. The model requires approximately 15.9 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does Thomson 1.0 Small support vision tasks?
No. The model has no vision capabilities.
Under what license is Thomson 1.0 Small released?
It is released under the Apache‑2.0 license.