Yi-Ko-34B-Instruct needs about 23.3 GB of memory at Q4_K_M (a 20.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 14 quants, from 12.9 GB (Q2_K) to 36.8 GB (Q8_0).
Yi-Ko-34B-Instruct: 34.6B parameter Llama-based instruction model
Yi-Ko-34B-Instruct is a 34.6B parameter Llama architecture model fine‑tuned with Korean and English corpora. It supports instruction following and generates text only. The model is available in multiple GGUF quantizations.
Good at
- Instruction following
- Korean and English text generation
- Large context handling
Limits
- No vision support
- Requires large VRAM for high‑quality quants
- License is other
Best for
- Chatbots needing Korean support
- Content creation in Korean/English
- Research prototyping
Who it’s for. Developers and researchers who need a large instruction‑tuned Llama model with Korean language capability. The model is suitable for local deployment via llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 12.9 GB | 14.5 GB | Too big | Get file → | |
| IQ3_XS | 14.4 GB | 15.9 GB | Too big | Get file → | |
| Q3_K_S | 15.1 GB | 16.6 GB | Too big | Get file → | |
| IQ3_S | 15.1 GB | 16.7 GB | Too big | Get file → | |
| IQ3_M | 15.7 GB | 17.2 GB | Too big | Get file → | |
| Q3_K_M | 16.8 GB | 18.3 GB | Too big | Get file → | |
| Q3_K_L | 18.3 GB | 19.8 GB | Too big | Get file → | |
| IQ4_XS | 18.8 GB | 20.3 GB | Too big | Get file → | |
| Q4_K_S | 19.7 GB | 21.2 GB | Too big | Get file → | |
| Q4_K_M | 20.8 GB | 22.3 GB | Too big | Get file → | |
| Q5_K_S | 23.9 GB | 25.4 GB | Too big | Get file → | |
| Q5_K_M | 24.5 GB | 26.0 GB | Too big | Get file → | |
| Q6_K | 28.4 GB | 29.9 GB | Too big | Get file → | |
| Q8_0 | 36.8 GB | 38.3 GB | Too big | Get file → |
For 8 GB VRAM use Q2_K (file size 12.94 GB, ~15.5 GB memory). For 12 GB VRAM use Q3_K_S (15.09 GB, ~17.6 GB memory). For 16 GB VRAM use Q4_K_M (20.8 GB, ~23.3 GB memory). Estimates are approximate.
What GPU do you need for Yi-Ko-34B-Instruct?
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 Q2_K (12.9 GB file, about 15.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (20.8 GB file, about 23.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (28.4 GB file, about 30.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (36.8 GB file, about 39.3 GB in use).
Which Yi-Ko-34B-Instruct quant should you choose?
Q4_K_M is the usual starting point for Yi-Ko-34B-Instruct: it balances file size and quality well. Here it is a 20.8 GB file.
The Q8_0 file is 36.8 GB, about 1.8 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 at 12.9 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 Yi-Ko-34B-Instruct
How much VRAM does Yi-Ko-34B-Instruct need?
About 23.3 GB at Q4_K_M with an 8K context window. That is the 20.8 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 Yi-Ko-34B-Instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Yi-Ko-34B-Instruct GGUF?
It depends on the quant: Q2_K is 12.9 GB, IQ3_XS is 14.4 GB, Q3_K_S is 15.1 GB, IQ3_S is 15.1 GB, IQ3_M is 15.7 GB, Q3_K_M is 16.8 GB and 8 more.
What context length does Yi-Ko-34B-Instruct support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.0 GB at 8K and 1.0 GB at 4K.
Where can I download Yi-Ko-34B-Instruct GGUF?
The files are on Hugging Face in the mradermacher/Yi-Ko-34B-Instruct-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 Yi-Ko-34B-Instruct use?
Hugging Face lists the license as other. 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 Yi-Ko-34B-Instruct on 8 GB VRAM?
Use the Q2_K quant; it requires about 15.5 GB of VRAM at 8 k context, which is above 8 GB, so it will not fit. A smaller quant like Q2_K is the closest but still exceeds 8 GB.
Does the model support vision inputs?
No, the model only accepts text input and produces text output.
What license applies to this model?
The model is released under an "other" license, not specified as open source.