K2 Horizon 3.7B Claude Opus Reasoning Distilled needs about 4.9 GB of memory at Q4_K_M (a 3.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 2.8 GB (Q2_K_L) to 5.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
K2 Horizon 3.7B Claude Opus Reasoning Distilled – a reasoning‑focused fine‑tune
K2 Horizon 3.7B Claude Opus Reasoning Distilled is a dense, decoder‑only model with 5.06B stored parameters. It is fine‑tuned on 8,000 Claude Opus and Sonnet reasoning traces to improve multi‑step problem solving, coding, and analytical tasks. The model supports a context window of up to 512K tokens.
Good at
- Multi‑step reasoning
- Coding and technical queries
- Mathematical problem solving
Limits
- No vision support
- Requires large VRAM for higher quants
- License is Apache‑2.0
Best for
- Academic research on reasoning models
- Developing agentic applications
- Testing structured problem‑solving
Who it’s for. Researchers and developers interested in open‑weight reasoning models. The model is suitable for those who need a compact yet capable reasoning engine and are comfortable working with GGUF files and llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K_L | 2.8 GB | 4.5 GB | Fits | Get file → | |
| Q4_K_M | 3.2 GB | 4.9 GB | Fits | Get file → | |
| Q6_K | 4.2 GB | 5.9 GB | Fits | Get file → | |
| Q8_0 | 5.4 GB | 7.1 GB | Fits | Get file → |
For 8 GB VRAM use Q2_K_L (file size 2.77 GB, estimated memory 4.5 GB). For 12 GB VRAM use Q4_K_M (3.16 GB, 4.9 GB). For 16 GB VRAM use Q6_K (4.16 GB, 5.9 GB). For 24 GB VRAM use Q8_0 (5.39 GB, 7.1 GB). Estimates are approximate.
What GPU do you need for K2 Horizon 3.7B Claude Opus Reasoning Distilled?
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: the best quant that fits is Q6_K (4.2 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (5.4 GB file, about 7.1 GB in use).
Which K2 Horizon 3.7B Claude Opus Reasoning Distilled quant should you choose?
Q4_K_M is the usual starting point for K2 Horizon 3.7B Claude Opus Reasoning Distilled: it balances file size and quality well. Here it is a 3.2 GB file.
The Q8_0 file is 5.4 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K_L at 2.8 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
Frequently asked questions about K2 Horizon 3.7B Claude Opus Reasoning Distilled
How much VRAM does K2 Horizon 3.7B Claude Opus Reasoning Distilled need?
About 4.9 GB at Q4_K_M with an 8K context window. That is the 3.2 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 K2 Horizon 3.7B Claude Opus Reasoning Distilled on an 8 GB GPU?
Yes, with Q8_0: the 5.4 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of K2 Horizon 3.7B Claude Opus Reasoning Distilled GGUF?
It depends on the quant: Q2_K_L is 2.8 GB, Q4_K_M is 3.2 GB, Q6_K is 4.2 GB, Q8_0 is 5.4 GB.
What context length does K2 Horizon 3.7B Claude Opus Reasoning Distilled support?
The GGUF header lists a trained context length of 524,288 tokens (512K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download K2 Horizon 3.7B Claude Opus Reasoning Distilled GGUF?
The files are on Hugging Face in the xtools-at/K2-Horizon-3.7B-Claude-Opus-Reasoning-Distilled-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 K2 Horizon 3.7B Claude Opus Reasoning Distilled 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 this model on 8 GB VRAM?
Yes, the Q2_K_L quant requires about 4.5 GB of VRAM at 8k context, which fits within 8 GB.
Does the model support image inputs?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.