Koa Express 31B Qat needs about 52.2 GB of memory at Q4_K_M (a 19.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 12.4 GB (Q2_K) to 19.5 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.
Koa Express 31B Qat – a 32.1B‑parameter Gemma4 model for reasoning and tool use
Koa Express 31B Qat is a 32.1B‑parameter Gemma4 model optimized for reasoning and tool usage. It supports a context length of 262144 tokens and is available in several static quantizations. The model is provided in GGUF format for use with llama.cpp.
Good at
- Reasoning tasks
- Tool integration
- Long‑context handling
Limits
- No vision support
- License not specified
- Large VRAM requirement for higher quants
Best for
- Complex reasoning workflows
- Tool‑enabled applications
- Long‑form content generation
Who it’s for. Developers building AI assistants that need deep reasoning and tool integration. Researchers requiring a large Gemma4 model with extensive context support.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 12.4 GB | 45.1 GB | Too big | Get file → | |
| Q3_K_S | 14.4 GB | 47.1 GB | Too big | Get file → | |
| Q3_K_M | 15.9 GB | 48.6 GB | Too big | Get file → | |
| Q3_K_L | 17.2 GB | 49.9 GB | Too big | Get file → | |
| IQ4_XS | 17.6 GB | 50.3 GB | Too big | Get file → | |
| Q4_K_S | 18.6 GB | 51.3 GB | Too big | Get file → | |
| Q4_K_M | 19.5 GB | 52.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (12.38 GB file, ~45.1 GB memory at 8k context). For 16 GB VRAM, Q3_K_S (14.37 GB file, ~47.1 GB memory) or Q3_K_M (15.89 GB file, ~48.6 GB memory). For 32 GB VRAM, Q4_K_M (19.48 GB file, ~52.2 GB memory) offers higher quality.
What GPU do you need for Koa Express 31B Qat?
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: the best quant that fits is Q3_K_S (14.4 GB file, about 47.1 GB in use).
Which Koa Express 31B Qat quant should you choose?
Q4_K_M is the usual starting point for Koa Express 31B Qat: it balances file size and quality well. Here it is a 19.5 GB file.
If memory is tight, the smallest file is Q2_K at 12.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Koa Express 31B Qat
How much VRAM does Koa Express 31B Qat need?
About 52.2 GB at Q4_K_M with an 8K context window. That is the 19.5 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 Koa Express 31B Qat on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 45.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Koa Express 31B Qat GGUF?
It depends on the quant: Q2_K is 12.4 GB, Q3_K_S is 14.4 GB, Q3_K_M is 15.9 GB, Q3_K_L is 17.2 GB, IQ4_XS is 17.6 GB, Q4_K_S is 18.6 GB and 1 more.
What context length does Koa Express 31B Qat support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 32.2 GB at 8K and 128.8 GB at 32K.
Where can I download Koa Express 31B Qat GGUF?
The files are on Hugging Face in the mradermacher/Koa-express-31B-qat-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Koa Express 31B Qat on 8 GB VRAM?
Use the Q2_K quant, which requires about 45.1 GB of memory at 8k context. 8 GB VRAM is insufficient for this model.
Does the model support vision tasks?
No, the model has no vision capabilities.
What is the maximum context length?
The model supports 262144 tokens of context.