KI

Huihui Kimi Linear REAP 35B A3B Instruct Abliterated

KimiGGUF by mradermacherUpdated 2026-02-16
Download on Hugging Face
Parameters35.1B
Context1024K
Layers27
Architecturekimi-linear
Smallest quant0.1 GB
Quick answer

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 24 quants, from 0.1 GB to 28.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 36.7 GB.

Huihui Kimi Linear REAP 35B A3B Instruct Abliterated – 35.1B parameter LLM

Huihui Kimi Linear REAP 35B A3B Instruct Abliterated is a 35.1B parameter model built on the Kimi linear architecture. It supports tool usage and is trained on a context length of 1,048,576 tokens. The model is released under the MIT license.

Good at

  • Tool integration
  • Large context handling
  • Instruction following

Limits

  • No vision support
  • Large memory requirement
  • No mixture of experts tuning

Best for

  • Complex instruction chains
  • Long document summarization
  • Code generation with tool calls

Who it’s for. Developers and researchers who need a large language model with tool integration and extensive context. The model is suitable for applications requiring detailed instruction following and long‑form content handling.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 9.8 GB
Too big Get file →
IQ1_S7.3 GB 17.0 GB
Too big Get file →
IQ1_M8.1 GB 17.8 GB
Too big Get file →
IQ2_XXS9.4 GB 19.1 GB
Too big Get file →
IQ2_XS10.5 GB 20.1 GB
Too big Get file →
IQ2_S10.6 GB 20.2 GB
Too big Get file →
IQ2_M11.6 GB 21.3 GB
Too big Get file →
Q2_K_S12.0 GB 21.7 GB
Too big Get file →
Q2_K12.9 GB 22.6 GB
Too big Get file →
IQ3_XXS13.6 GB 23.3 GB
Too big Get file →
IQ3_XS14.5 GB 24.1 GB
Too big Get file →
IQ3_S15.3 GB 25.0 GB
Too big Get file →
Q3_K_S15.3 GB 25.0 GB
Too big Get file →
IQ3_M15.5 GB 25.1 GB
Too big Get file →
Q3_K_M16.8 GB 26.5 GB
Too big Get file →
Q3_K_L18.3 GB 28.0 GB
Too big Get file →
IQ4_XS18.8 GB 28.5 GB
Too big Get file →
Q4_020.0 GB 29.6 GB
Too big Get file →
Q4_K_S20.0 GB 29.7 GB
Too big Get file →
Q4_K_M21.3 GB 30.9 GB
Too big Get file →
Q4_122.1 GB 31.8 GB
Too big Get file →
Q5_K_S24.3 GB 33.9 GB
Too big Get file →
Q5_K_M24.9 GB 34.6 GB
Too big Get file →
Q6_K28.9 GB 38.5 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 7.31 GB, memory 17 GB at 8 k context). For 16 GB VRAM, IQ2_XS (10.45 GB, 20.1 GB). For 24 GB VRAM, Q3_K_M (16.84 GB, 26.5 GB). Estimates are approximate.

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: the best quant that fits is the main file (0.1 GB file, about 9.8 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 9.8 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ3_XXS (13.6 GB file, about 23.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_1 (22.1 GB file, about 31.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (28.9 GB file, about 38.5 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.

If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturekimi-linear
Parameters35.1B (approximate, mixture of experts)
Active parameters3B
Layers27
Trained context1,048,576 tokens
KV cache (fp16)1094 KB per token

Source

Quantized bymradermacher
FamilyKimi
Licensemit
Downloads (HF)970
Last updated2026-02-16

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 9.8 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: file is 0.1 GB, IQ1_S is 7.3 GB, IQ1_M is 8.1 GB, IQ2_XXS is 9.4 GB, IQ2_XS is 10.5 GB, IQ2_S is 10.6 GB and 18 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-i1-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?

Use the IQ1_S quant, which requires about 17 GB of VRAM at 8 k context. It is the smallest quant that fits within 8 GB VRAM constraints.

Does the model support image inputs?

No, the model does not have vision capabilities. It is text‑only.

What license applies to this model?

The model is released under the MIT license, allowing free use and modification.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Kimi models

All Kimi →

Other large models

All large models →