K2 IMat needs about 50.1 GB of memory at Q3_K_S (a 28.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 14.2 GB (IQ1_S) to 130.6 GB.
K2 IMat, a 65.3B‑parameter LLM quantized for llama.cpp
K2 IMat is a 65.3B‑parameter model based on LLM360/K2. It supports 2048‑token context and is released under Apache‑2.0. The model is available in multiple llama.cpp quantizations.
Good at
- Large‑scale text generation
- Domain‑specific knowledge
- Fast inference on GPUs
Limits
- No vision support
- Requires 8k context for memory estimates
- License is Apache‑2.0
Best for
- Chat applications
- Content creation
- Research prototyping
Who it’s for. Developers and researchers who need a large language model that can run on llama.cpp. The model is suitable for those who can manage the memory requirements of a 65.3B‑parameter LLM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 14.2 GB | 20.1 GB | Too big | Get file → | |
| IQ1_M | 15.4 GB | 21.3 GB | Too big | Get file → | |
| IQ2_XXS | 17.5 GB | 23.3 GB | Too big | Get file → | |
| IQ2_XS | 19.3 GB | 25.1 GB | Too big | Get file → | |
| IQ2_S | 20.8 GB | 26.7 GB | Too big | Get file → | |
| Q2_K_S | 22.0 GB | 27.8 GB | Too big | Get file → | |
| IQ2_M | 22.4 GB | 28.3 GB | Too big | Get file → | |
| Q2_K | 24.1 GB | 30.0 GB | Too big | Get file → | |
| IQ3_XXS | 24.7 GB | 30.5 GB | Too big | Get file → | |
| IQ3_XS | 26.6 GB | 32.5 GB | Too big | Get file → | |
| IQ3_S | 28.2 GB | 34.0 GB | Too big | Get file → | |
| Q3_K_S | 28.2 GB | 34.0 GB | Too big | Get file → | |
| IQ3_M | 29.8 GB | 35.7 GB | Too big | Get file → | |
| Q3_K | 31.6 GB | 37.5 GB | Too big | Get file → | |
| Q3_K_L | 34.6 GB | 40.5 GB | Too big | Get file → | |
| IQ4_XS | 34.8 GB | 40.6 GB | Too big | Get file → | |
| IQ4_NL | 36.8 GB | 42.7 GB | Too big | Get file → | |
| Q4_K_S | 37.1 GB | 42.9 GB | Too big | Get file → | |
| Q4_K | 39.3 GB | 45.2 GB | Too big | Get file → | |
| Q5_K_S | 44.9 GB | 50.8 GB | Too big | Get file → | |
| Q5_K | 46.2 GB (2 parts) | 52.1 GB | Too big | Get file → | |
| Q6_K | 53.6 GB (3 parts) | 59.4 GB | Too big | Get file → | |
| Q8_0 | 69.4 GB (3 parts) | 75.2 GB | Too big | Get file → | |
| — | 130.6 GB (6 parts) | 136.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (14.21 GB file, 36.2 GB memory at 8k context). For 16 GB VRAM, IQ2_S (20.78 GB file, 42.8 GB memory) or Q2_K_S (21.98 GB file, 44 GB memory). For 24 GB VRAM, Q3_K (31.63 GB file, 53.6 GB memory) or Q4_K_S (37.06 GB file, 59 GB memory).
What GPU do you need for K2 IMat?
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 IQ3_XXS (24.7 GB file, about 46.6 GB in use).
Which K2 IMat quant should you choose?
Q3_K_S (28.2 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is IQ1_S at 14.2 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 K2 IMat
How much VRAM does K2 IMat need?
About 50.1 GB at Q3_K_S with an 8K context window. That is the 28.2 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 IMat on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 36.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of K2 IMat GGUF?
It depends on the quant: IQ1_S is 14.2 GB, IQ1_M is 15.4 GB, IQ2_XXS is 17.5 GB, IQ2_XS is 19.3 GB, IQ2_S is 20.8 GB, Q2_K_S is 22.0 GB and 18 more.
What context length does K2 IMat support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 21.5 GB at 8K and 5.4 GB at 2K.
Where can I download K2 IMat GGUF?
The files are on Hugging Face in the legraphista/K2-IMat-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 IMat 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 K2 IMat on 8 GB VRAM?
Use the IQ1_S quantization; it requires about 36.2 GB memory at 8k context, which is above 8 GB, so it is not feasible on 8 GB VRAM.
What is the context length supported by K2 IMat?
The model supports 2048 tokens of context.
Is K2 IMat licensed for commercial use?
It is released under the Apache‑2.0 license, which allows commercial use with attribution.