KI

Kimi Linear 48B A3B Base

KimiGGUF by mradermacherUpdated 2026-02-15
Download on Hugging Face
Parameters49.1B
Context1024K
Layers27
Architecturekimi-linear
Smallest quant18.0 GB
Quick answer

Kimi Linear 48B A3B Base 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 11 quants, from 18.0 GB (Q2_K) to 52.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 36.7 GB.

Kimi Linear 48B A3B Base – a 49.1B parameter hybrid linear attention model

Kimi Linear 48B A3B Base is a 49.1B parameter model built on the Kimi‑Linear architecture. It uses Kimi Delta Attention to reduce KV cache usage and achieve high throughput on long contexts. The model is released under the MIT license and supports tool usage.

Good at

  • Long‑context inference up to 1M tokens
  • High decoding speed with linear attention
  • Efficient KV cache usage

Limits

  • Requires 8k context for memory estimates
  • No vision support
  • Mixture of experts may increase memory usage

Best for

  • Chatbots needing long context
  • Research on large‑scale language modeling
  • Deployments on GPUs with limited VRAM

Who it’s for. Developers and researchers who need a large‑parameter model with efficient long‑context performance. The model is open‑source and can be run with llama.cpp or vllm.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K18.0 GB 27.7 GB
Too big Get file →
Q3_K_S21.3 GB 31.0 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_XS26.5 GB 36.1 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 →
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 →
Q8_052.2 GB 61.9 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (file size 18.03 GB, estimated 27.7 GB memory at 8k context). For 16 GB VRAM, Q4_K_M (29.7 GB, 39.4 GB memory) or Q5_K_S (33.89 GB, 43.6 GB memory) are suitable. For 32 GB VRAM, Q6_K (40.36 GB, 50 GB memory) or Q8_0 (52.25 GB, 61.9 GB memory) provide higher quality.

What GPU do you need for Kimi Linear 48B A3B Base?

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 Q3_K_S (21.3 GB file, about 31.0 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 Base quant should you choose?

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

The Q8_0 file is 52.2 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 18.0 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

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)611
Last updated2026-02-15

Frequently asked questions about Kimi Linear 48B A3B Base

How much VRAM does Kimi Linear 48B A3B Base 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 Base on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 27.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Kimi Linear 48B A3B Base GGUF?

It depends on the quant: Q2_K is 18.0 GB, Q3_K_S is 21.3 GB, Q3_K_M is 23.5 GB, Q3_K_L is 25.5 GB, IQ4_XS is 26.5 GB, Q4_K_S is 28.0 GB and 5 more.

What context length does Kimi Linear 48B A3B Base 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 Base GGUF?

The files are on Hugging Face in the mradermacher/Kimi-Linear-48B-A3B-Base-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 Base 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 Kimi Linear 48B A3B Base on 8 GB VRAM?

The Q2_K quant requires about 27.7 GB memory at 8k context, so 8 GB VRAM is insufficient.

Does this model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the MIT license.

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

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Kimi models

All Kimi →

Other large models

All large models →