KI

cerebras/Kimi-Linear-REAP-35B-A3B-Instruct

KimiGGUF by lunvUpdated 2026-01-18
Download on Hugging Face
Parameters35.1B
Context1024K
Layers27
Architecturekimi-linear
Smallest quant15.5 GB
Quick answer

cerebras/Kimi-Linear-REAP-35B-A3B-Instruct needs about 40.2 GB of memory at Q5_K_S (a 24.3 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 5 quants, from 15.5 GB (IQ3_M) to 70.3 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 61.6 GB.

cerebras/Kimi-Linear-REAP-35B-A3B-Instruct is a 35.1B-parameter Kimi model in GGUF format, quantized by lunv. Its trained context length is 1024K tokens. The repository has 5 quant files, from 15.5 GB (IQ3_M) to 70.3 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_M15.5 GB 31.4 GB
Too big Get file →
IQ4_NL20.0 GB 35.9 GB
Too big Get file →
Q5_K_S24.3 GB 40.2 GB
Too big Get file →
Q6_K28.9 GB 44.8 GB
Too big Get file →
F1670.3 GB 86.2 GB
Too big Get file →

What GPU do you need for cerebras/Kimi-Linear-REAP-35B-A3B-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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is IQ3_M (15.5 GB file, about 31.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (28.9 GB file, about 44.8 GB in use).

Which cerebras/Kimi-Linear-REAP-35B-A3B-Instruct quant should you choose?

Q5_K_S (24.3 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is IQ3_M at 15.5 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

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)1836 KB per token

Source

Quantized bylunv
FamilyKimi
Licensemit
Downloads (HF)94
Last updated2026-01-18

Frequently asked questions about cerebras/Kimi-Linear-REAP-35B-A3B-Instruct

How much VRAM does cerebras/Kimi-Linear-REAP-35B-A3B-Instruct need?

About 40.2 GB at Q5_K_S with an 8K context window. That is the 24.3 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 cerebras/Kimi-Linear-REAP-35B-A3B-Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 31.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of cerebras/Kimi-Linear-REAP-35B-A3B-Instruct GGUF?

It depends on the quant: IQ3_M is 15.5 GB, IQ4_NL is 20.0 GB, Q5_K_S is 24.3 GB, Q6_K is 28.9 GB, F16 is 70.3 GB.

What context length does cerebras/Kimi-Linear-REAP-35B-A3B-Instruct 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 15.4 GB at 8K and 61.6 GB at 32K.

Where can I download cerebras/Kimi-Linear-REAP-35B-A3B-Instruct GGUF?

The files are on Hugging Face in the lunv/Kimi-Linear-REAP-35B-A3B-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 cerebras/Kimi-Linear-REAP-35B-A3B-Instruct 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.

Other GGUFs of Kimi-Linear-REAP-35B-A3B-Instruct

Similar models

Browse all →

More Kimi models

All Kimi →

Other large models

All large models →