Huihui Kimi Linear REAP 35B A3B Instruct Abliterated needs about 30.9 GB of memory at Q4_K_M (a 21.3 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 11 quants, from 12.9 GB (Q2_K) to 37.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 36.7 GB.
Huihui Kimi Linear REAP 35B A3B Instruct Abliterated – a 35.1B parameter LLM with tool usage
This model is a 35.1B parameter Kimi‑linear architecture. It supports tool usage and is released under the MIT license. The model was trained on a context of 1,048,576 tokens.
Good at
- Tool usage
- Large context handling
- Mixture of experts
Limits
- No vision support
- Requires large VRAM for higher quants
- No other language support listed
Best for
- Chatbot with tool integration
- Long‑form content generation
- Research prototyping
Who it’s for. Developers and researchers who need a large language model with tool‑usage capability and a permissive MIT license. Suitable for applications requiring extensive context handling.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 12.9 GB | 22.6 GB | Too big | Get file → | |
| Q3_K_S | 15.3 GB | 25.0 GB | Too big | Get file → | |
| Q3_K_M | 16.8 GB | 26.5 GB | Too big | Get file → | |
| Q3_K_L | 18.3 GB | 28.0 GB | Too big | Get file → | |
| IQ4_XS | 19.0 GB | 28.6 GB | Too big | Get file → | |
| Q4_K_S | 20.0 GB | 29.7 GB | Too big | Get file → | |
| Q4_K_M | 21.3 GB | 30.9 GB | Too big | Get file → | |
| Q5_K_S | 24.3 GB | 33.9 GB | Too big | Get file → | |
| Q5_K_M | 24.9 GB | 34.6 GB | Too big | Get file → | |
| Q6_K | 28.9 GB | 38.5 GB | Too big | Get file → | |
| Q8_0 | 37.4 GB | 47.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (22.6 GB memory) or Q3_K_S (25 GB). For 16 GB VRAM, Q4_K_M (30.9 GB) is a good balance. For 32 GB VRAM, Q6_K (38.5 GB) or Q8_0 (47 GB) provide higher quality.
What GPU do you need for Huihui Kimi Linear REAP 35B A3B Instruct Abliterated?
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: the best quant that fits is Q2_K (12.9 GB file, about 22.6 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (21.3 GB file, about 30.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (37.4 GB file, about 47.0 GB in use).
Which Huihui Kimi Linear REAP 35B A3B Instruct Abliterated quant should you choose?
Q4_K_M is the usual starting point for Huihui Kimi Linear REAP 35B A3B Instruct Abliterated: it balances file size and quality well. Here it is a 21.3 GB file.
The Q8_0 file is 37.4 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
Frequently asked questions about Huihui Kimi Linear REAP 35B A3B Instruct Abliterated
How much VRAM does Huihui Kimi Linear REAP 35B A3B Instruct Abliterated need?
About 30.9 GB at Q4_K_M with an 8K context window. That is the 21.3 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 Huihui Kimi Linear REAP 35B A3B Instruct Abliterated on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 22.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Huihui Kimi Linear REAP 35B A3B Instruct Abliterated GGUF?
It depends on the quant: Q2_K is 12.9 GB, Q3_K_S is 15.3 GB, Q3_K_M is 16.8 GB, Q3_K_L is 18.3 GB, IQ4_XS is 19.0 GB, Q4_K_S is 20.0 GB and 5 more.
What context length does Huihui Kimi Linear REAP 35B A3B Instruct Abliterated support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 9.2 GB at 8K and 36.7 GB at 32K.
Where can I download Huihui Kimi Linear REAP 35B A3B Instruct Abliterated GGUF?
The files are on Hugging Face in the mradermacher/Huihui-Kimi-Linear-REAP-35B-A3B-Instruct-abliterated-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 Huihui Kimi Linear REAP 35B A3B Instruct Abliterated use?
Hugging Face lists the license as mit. 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?
Only the smallest quants such as Q2_K or Q3_K_S can fit, but they still require more than 8 GB VRAM. Use a larger GPU if possible.
Does this model support vision?
No, the model does not have vision capabilities.
What license does it use?
The model is released under the MIT license.