Ourbox 35B JGOS needs about 22.3 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 8.2 GB (IQ1_M) to 21.2 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
34.7B Korean‑specialized reasoning MoE model
Ourbox 35B JGOS is a 34.7B‑parameter mixture‑of‑experts model built on Qwen3.6‑35B‑A3B. It specializes in Korean language reasoning and supports a 262 144‑token context. The model is released under Apache 2.0 and runs with stock llama.cpp.
Good at
- Korean reasoning
- Large context (262K tokens)
- Tool usage
Limits
- No vision support
- Requires 8 GB VRAM for Q4_K_M
- CPU only on low‑end devices
Best for
- Korean language chat
- Long‑form Korean content generation
- Reasoning tasks on edge devices
Who it’s for. Developers needing a Korean‑specialized reasoning model that can run on consumer GPUs or CPUs. The model is suitable for edge deployments and local inference with llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_M | 8.2 GB | 9.4 GB | Too big | Get file → | |
| Q2_K | 12.9 GB | 14.1 GB | Too big | Get file → | |
| Q3_K_M | 16.8 GB | 17.9 GB | Too big | Get file → | |
| Q4_K_M | 21.2 GB | 22.3 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (file size 21.17 GB, estimated 22.3 GB memory at 8 k context). If more VRAM is available, Q3_K_M (16.76 GB, 17.9 GB memory) offers better quality. IQ1_M (8.24 GB, 9.4 GB memory) is the lightest option for very low‑end hardware.
What GPU do you need for Ourbox 35B JGOS?
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 IQ1_M (8.2 GB file, about 9.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q2_K (12.9 GB file, about 14.1 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (21.2 GB file, about 22.3 GB in use).
Which Ourbox 35B JGOS quant should you choose?
Q4_K_M is the usual starting point for Ourbox 35B JGOS: it balances file size and quality well. Here it is a 21.2 GB file.
If memory is tight, the smallest file is IQ1_M at 8.2 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 Ourbox 35B JGOS
How much VRAM does Ourbox 35B JGOS need?
About 22.3 GB at Q4_K_M with an 8K context window. That is the 21.2 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 Ourbox 35B JGOS on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ourbox 35B JGOS GGUF?
It depends on the quant: IQ1_M is 8.2 GB, Q2_K is 12.9 GB, Q3_K_M is 16.8 GB, Q4_K_M is 21.2 GB.
What context length does Ourbox 35B JGOS 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 Ourbox 35B JGOS GGUF?
The files are on Hugging Face in the FINAL-Bench/Ourbox-35B-JGOS-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 Ourbox 35B JGOS 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.
Does the model support vision or image input?
No, the model has no vision capabilities and only processes text.
What license applies to this model?
The model is released under the Apache 2.0 license.