---
language: en
pipeline_tag: text-generation
tags:
- mlx
library_name: mlx
base_model:
- moonshotai/Kimi-K2.6
---

[Kimi K2.6](https://huggingface.co/moonshotai/Kimi-K2.6) optimized to run _comfortably_
on a Mac Studio M3 512. This is the smaller, compact version. Quality-first
version [here](https://huggingface.co/spicyneuron/Kimi-K2.6-MLX-3.6bit).

- A mixed-precision quant that balances speed, memory, and accuracy.
- 3-bit baseline with important layers at 8-bit and BF16.
- Fits into ~430 GB memory, leaving plenty of room to run a smaller, faster utility model (ex: Qwen 3.6 35B, Gemma 4 26B).
- This quant does not support image input.

# Usage

```sh
# Start server at http://localhost:8080/v1/chat/completions
# Kimi K2.6 requires tiktoken + remote code for the tokenizer
uvx --from mlx-lm --with tiktoken \
  mlx_lm.server \
    --host 127.0.0.1 \
    --port 8080 \
    --trust-remote-code \
    --model spicyneuron/Kimi-K2.6-MLX-3.3bit
```

# Benchmarks

metric | 3.6 bit | 3.3 bit (this model)
--- | --- | ---
bpw | 3.578 | 3.331
peak memory (1024/512) | 460.444 | 428.735
prompt tok/s (1024) | 221.704 ± 0.057 | 223.613 ± 0.098
gen tok/s (512) | 21.095 ± 0.070 | 21.363 ± 0.035
kl mean | 0.022 ± 0.001 | 0.051 ± 0.002
kl p95 | 0.053 ± 0.001 | 0.113 ± 0.002
perplexity | 3.559 ± 0.021 | 3.550 ± 0.020
hellaswag | 0.594 ± 0.022 | 0.590 ± 0.022
piqa | 0.848 ± 0.016 | 0.852 ± 0.016
winogrande | 0.670 ± 0.021 | 0.690 ± 0.021

Tested on a Mac Studio M3 Ultra with:

```
mlx_lm.kld --baseline-model path/to/mlx-full-precision
mlx_lm.perplexity --sequence-length 512 --seed 123
mlx_lm.benchmark --prompt-tokens 1024 --generation-tokens 512 --num-trials 5
mlx_lm.evaluate --tasks hellaswag --seed 123 --num-shots 0 --limit 500
mlx_lm.evaluate --tasks piqa --seed 123 --num-shots 0 --limit 500
mlx_lm.evaluate --tasks winogrande --seed 123 --num-shots 0 --limit 500
```

Note:

- `mlx_lm.kld` is approximate, based on `top_k` not full logits. Here's the [code](https://github.com/ml-explore/mlx-lm/pull/1146).
- Kimi K2.6 KL divergence calculated against the largest quant I could run locally (~490 GB), so real KL is higher.

# Methodology

Quantized with a [mlx-lm fork](https://github.com/ml-explore/mlx-lm/pull/922),
drawing inspiration from Unsloth/AesSedai/ubergarm style mixed-precision GGUFs.
MLX quantization options differ from llama.cpp, but the principles are the
same:

- Sensitive layers like MoE routing, attention, and output embeddings get higher precision
- More tolerant layers like MoE experts get lower precision