KI

Kimi Linear 48B A3B Instruct

KimiGGUF by mradermacherUpdated 2026-02-16
Download on Hugging Face
Parameters49.1B
Context1024K
Layers27
Architecturekimi-linear
Smallest quant0.2 GB
Quick answer

Kimi Linear 48B A3B Instruct needs about 39.4 GB of memory at Q4_K_M (a 29.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 24 quants, from 0.2 GB to 40.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 36.7 GB.

Kimi Linear 48B A3B Instruct – large‑scale linear attention model

Kimi Linear 48B A3B Instruct is a 49.1B parameter model with 3B active parameters and a mixture of experts. It supports up to 1,048,576 context tokens and delivers 6.3× faster TPOT and up to 6× decoding speed compared to full attention.

Good at

  • Long‑context inference
  • High‑throughput decoding
  • Efficient KV cache usage

Limits

  • Requires large VRAM for full precision
  • Supports only text, no vision
  • Context limited to 1,048,576 tokens

Best for

  • Long‑form content generation
  • Reinforcement learning tasks
  • Large‑context summarization

Who it’s for. Developers and researchers who need high‑throughput, long‑context language models. Teams deploying on GPUs with sufficient VRAM can leverage its efficient linear attention architecture.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.2 GB 9.8 GB
Too big Get file →
IQ1_S10.1 GB 19.8 GB
Too big Get file →
IQ1_M11.2 GB 20.9 GB
Too big Get file →
IQ2_XXS13.0 GB 22.7 GB
Too big Get file →
IQ2_XS14.5 GB 24.2 GB
Too big Get file →
IQ2_S14.7 GB 24.3 GB
Too big Get file →
IQ2_M16.1 GB 25.8 GB
Too big Get file →
Q2_K_S16.7 GB 26.3 GB
Too big Get file →
Q2_K18.0 GB 27.7 GB
Too big Get file →
IQ3_XXS19.0 GB 28.7 GB
Too big Get file →
IQ3_XS20.2 GB 29.8 GB
Too big Get file →
IQ3_S21.3 GB 31.0 GB
Too big Get file →
Q3_K_S21.3 GB 31.0 GB
Too big Get file →
IQ3_M21.5 GB 31.2 GB
Too big Get file →
Q3_K_M23.5 GB 33.2 GB
Too big Get file →
Q3_K_L25.5 GB 35.2 GB
Too big Get file →
IQ4_XS26.3 GB 35.9 GB
Too big Get file →
Q4_027.9 GB 37.5 GB
Too big Get file →
Q4_K_S28.0 GB 37.6 GB
Too big Get file →
Q4_K_M29.7 GB 39.4 GB
Too big Get file →
Q4_130.8 GB 40.5 GB
Too big Get file →
Q5_K_S33.9 GB 43.6 GB
Too big Get file →
Q5_K_M34.9 GB 44.5 GB
Too big Get file →
Q6_K40.4 GB 50.0 GB
Too big Get file →

Memory estimates are approximate. For 16GB VRAM, consider IQ2_XS (file size 14.52GB, 24.2GB memory at 8k context) or Q4_0 (27.87GB, 37.5GB memory). For larger VRAM, Q5_K_S (33.89GB, 43.6GB memory) offers a higher quality trade‑off.

What GPU do you need for Kimi Linear 48B 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: the best quant that fits is the main file (0.2 GB file, about 9.8 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 9.8 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ2_XXS (13.0 GB file, about 22.7 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ3_M (21.5 GB file, about 31.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q5_K_M (34.9 GB file, about 44.5 GB in use).

Which Kimi Linear 48B A3B Instruct quant should you choose?

Q4_K_M is the usual starting point for Kimi Linear 48B A3B Instruct: it balances file size and quality well. Here it is a 29.7 GB file.

If memory is tight, the smallest file is the first one in the table at 0.2 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
Parameters49.1B (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)1,405
Last updated2026-02-16

Frequently asked questions about Kimi Linear 48B A3B Instruct

How much VRAM does Kimi Linear 48B A3B Instruct need?

About 39.4 GB at Q4_K_M with an 8K context window. That is the 29.7 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 Kimi Linear 48B A3B Instruct 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 Kimi Linear 48B A3B Instruct GGUF?

It depends on the quant: file is 0.2 GB, IQ1_S is 10.1 GB, IQ1_M is 11.2 GB, IQ2_XXS is 13.0 GB, IQ2_XS is 14.5 GB, IQ2_S is 14.7 GB and 18 more.

What context length does Kimi Linear 48B 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 9.2 GB at 8K and 36.7 GB at 32K.

Where can I download Kimi Linear 48B A3B Instruct GGUF?

The files are on Hugging Face in the mradermacher/Kimi-Linear-48B-A3B-Instruct-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 Kimi Linear 48B 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.

Can I run this model on 8GB VRAM?

No, memory estimates exceed 8GB for all available quantizations.

What context length does it support?

It supports up to 1,048,576 tokens.

Is the model licensed under MIT?

Yes, the model is released under the MIT license.

Other GGUFs of Kimi-Linear-48B-A3B-Instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Kimi models

All Kimi →

Other large models

All large models →