K

Kimi Linear 48B A3B Instruct

Oct 2025
KKimi Linear 48B A3B Instruct
Compare in
on
—per task?
$0.08 / $0.40per 1M in / out?
—output speed?
1Mcontext

Ranking?

Alternatives?

Run it yourself

estimate
Fits on✗ 8 GB (phone, laptop)✗ 16 GB✗ 24 GB GPU✓ 48 GB GPU · compressed✓ 80 GB GPU · 8-bit
LicenceMITfree for commercial use

Benchmarks

all categories
Chat & Knowledge
GPQA Diamond41.2#280
Coding
Agents & Tool Use
Writing & Language

FAQ

How much does Kimi Linear 48B A3B Instruct cost?›

$0.08 per 1M input tokens and $0.40 per 1M output tokens (cheapest host: Featherless).

Is Kimi Linear 48B A3B Instruct free to use?›

There is no free API; the cheapest paid price is $0.08 per 1M input tokens. The weights are open, so you can run it yourself.

How good is Kimi Linear 48B A3B Instruct, and what is it best at?›

#333 of 336 in Chat & Knowledge, #119 of 239 in Coding, #229 of 242 in Agents & Tool Use, #215 of 245 in Writing & Language.

Is Kimi Linear 48B A3B Instruct better than Llama 3.1 Nemotron Nano 4B v1.1?›

On AA Intelligence Index 4.3.2, Kimi Linear 48B A3B Instruct scores 7.3 vs 7.3 — about the same.

How can I use Kimi Linear 48B A3B Instruct?›

Through the API of Featherless.

What is the context window of Kimi Linear 48B A3B Instruct?›

1M tokens.

When was Kimi Linear 48B A3B Instruct released? Is there a newer version?›

Released 2025-10-30. It is the current version in its line.

Is Kimi Linear 48B A3B Instruct open source?›

Yes, the weights are open (MIT licence).

Can I run Kimi Linear 48B A3B Instruct locally?›

The weights are open and can be self-hosted; hardware needs are not confirmed yet.

Can Kimi Linear 48B A3B Instruct read images?›

No, it accepts text only.

What is Kimi Linear 48B A3B Instruct?›

Kimi Linear 48B A3B Instruct is an open-weights language model from Kimi, released Oct 2025.

What are the best alternatives to Kimi Linear 48B A3B Instruct?›

Agnes 2.5 Pro Beta (cheaper), GPT-6 Luna (better), Qwen3.8 27B (open weights).