---
title: K2-Horizon-0.9B-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/K2-Horizon-0.9B-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/K2-Horizon-0.9B-8bit.md"
repository: mlx-community/K2-Horizon-0.9B-8bit
last_updated: 2026-09-30
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - k2_horizon
architectures:
  - K2HorizonForCausalLM
base_model:
  - IFM/K2-Horizon-0.9B
base_model_relation: quantized
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 48
stars: 0
tags:
  - mlx
  - quantized
  - dense
  - k2-horizon
---

# K2-Horizon-0.9B-8bit

> K2-Horizon-0.9B-8bit - mlx-community 在 ModelScope 开源的模型。K2-Horizon-0.9B (MLX, 8-bit)

mlx-community/K2-Horizon-0.9B-8bit 是 ModelScope 魔搭社区上的text-generation模型，采用 apache-2.0 许可，基于 IFM/K2-Horizon-0.9B 构建。

- **Repository**: mlx-community/K2-Horizon-0.9B-8bit
- **License**: apache-2.0
- **Tasks**: text-generation
- **Base model**: IFM/K2-Horizon-0.9B
- **Tags**: mlx, quantized, dense, k2-horizon
- **Downloads**: 48
- **Stars**: 0
- **Last updated**: 2026-09-30

Source: https://www.modelscope.cn/models/mlx-community/K2-Horizon-0.9B-8bit

---

# K2-Horizon-0.9B (MLX, 8-bit)

**8-bit** MLX quantization of [IFM/K2-Horizon-0.9B](https://huggingface.co/IFM/K2-Horizon-0.9B), converted from revision `fa7f5de`. **8.5 bits/weight effective**, 1.2 GB on disk. For Apple silicon.

K2-Horizon-0.9B is IFM's compact dense K2-Horizon model: a 0.9B-class decoder-only model distilled from domain teachers, with a 128K (131,072-token) context window through YaRN RoPE scaling.

## Requirements

mlx-lm doesn't support the `k2_horizon` architecture yet. There's an open request: [mlx-lm#1876](https://github.com/ml-explore/mlx-lm/issues/1876). Until support lands, **this repo ships the MLX model code** ([`k2_horizon.py`](./k2_horizon.py)), which mlx-lm loads through the `model_file` entry in `config.json`. So the released mlx-lm works as-is:

```bash
pip install -U mlx-lm
```

Pass `--trust-remote-code` (or `trust_remote_code=True`). mlx-lm 0.31.3 loads the file without it, but newer versions require it. The file runs on your machine, so read it first if you like; its comments describe how it differs from IFM's PyTorch code.

Once K2-Horizon support lands in a released mlx-lm, this repo will be updated to use it. If something breaks after that, open a discussion here asking for a re-upload.

## How it was quantized

`mlx_lm.convert -q --q-bits 8 --q-group-size 64` (integer affine quantization, bf16 scales and biases). All linear layers and the embeddings are 8-bit. WikiText-2 perplexity is within +0.3% of bf16, so it is effectively lossless.

## Memory

Peak **1.3 GB** for a short prompt; fits a **8 GB** Mac. The KV cache adds about 56 KB per token in bf16 (7.0 GB at 128K tokens), so long contexts need more memory; `--max-kv-size` and KV-cache quantization (`--kv-bits 8`, where available) reduce it.

## Conversion check

The MLX implementation was checked against IFM's PyTorch code (`modeling_k2_horizon.py`) in **fp32 on the real weights of this model**:

- Layer by layer, all 28 layers match to a relative error of 4e-6 or better, and the next-token predictions agree at every position.
- Token by token: the full model in fp32 greedily generated with the KV cache, and the PyTorch model picked the same token at every step (320/320 tokens across English, code, math and Chinese prompts). Cached and uncached outputs also agree at every step.

Smoke-tested after conversion with released mlx-lm 0.31.3: `17 * 23` → `391` and "capital of Australia" → `Canberra`, both ending normally. On a **Mac Studio M4 Max 128GB**: 306.9 tok/s generation, peak 1.3 GB (short prompt).

## Benchmarks (all K2-Horizon-0.9B MLX variants)

WikiText-2 test perplexity (128 × 512 tokens, lower is better) and generation speed on an M4 Max 128GB, all measured the same way:

| | [bf16](https://huggingface.co/mlx-community/K2-Horizon-0.9B-bf16) | [8-bit](https://huggingface.co/mlx-community/K2-Horizon-0.9B-8bit) | [4-bit](https://huggingface.co/mlx-community/K2-Horizon-0.9B-4bit) |
|---|---|---|---|
| Bits/weight | 16 | 8.5 | 6.4 |
| Disk | 2.2 GB | 1.2 GB | 0.9 GB |
| Peak memory | 2.2 GB | 1.3 GB | 1.0 GB |
| WikiText-2 perplexity | 18.654 | 18.713 (+0.3%) | 19.703 (+5.6%) |
| Generation | 195.7 tok/s | 306.9 tok/s | 379.8 tok/s |

Perplexity is a coarse signal. Test the versions on your own workload before picking one. Other K2-Horizon sizes: the [K2-Horizon collection](https://huggingface.co/collections/mlx-community/k2-horizon).

## Usage

```bash
mlx_lm.generate --model mlx-community/K2-Horizon-0.9B-8bit --trust-remote-code --prompt "Explain mixture-of-experts in two sentences." --max-tokens 2048
```

```python
from mlx_lm import load, generate

# Newer mlx-lm versions need trust_remote_code=True; on mlx-lm 0.31.3 use load("mlx-community/K2-Horizon-0.9B-8bit").
model, tokenizer = load("mlx-community/K2-Horizon-0.9B-8bit", trust_remote_code=True)
messages = [{"role": "user", "content": "Explain mixture-of-experts in two sentences."}]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
print(generate(model, tokenizer, prompt, max_tokens=2048))
```

`mlx_lm.chat` and `mlx_lm.server` take the same `--trust-remote-code` flag.

The model thinks before it answers, inside `<ifm|think> … </ifm|think>`. Leave room for that in `max_tokens`. The effort level is set with `reasoning_effort` in the chat template: `"high"` (default), `"medium"` or `"low"`, e.g. `apply_chat_template(messages, add_generation_prompt=True, reasoning_effort="low")`.

**Notes:**

- **Server output:** mlx-lm doesn't recognize the `<ifm|think>` tags yet, so `mlx_lm.server` returns the thinking text inside `content`, before `</ifm|think>`, rather than in a separate `reasoning` field. K2-Horizon's tool-call format isn't parsed yet either.
- **End-of-turn token:** the original `generation_config.json` lists only `<|endoftext|>` (id 1) as EOS, but the chat template ends each turn with `<|ifm|im_end|>` (id 64019). This repo adds 64019 to `eos_token_id`, like the other K2-Horizon models, so generation stops at the end of the answer and `<|ifm|im_end|>` does not appear in the output.
- **dtype:** the original config says `float32`, but the checkpoint weights are bf16. The config here says `bfloat16`, so no tool upcasts the weights.
- **YaRN:** RoPE uses YaRN (factor 16, original 8K context). The MLX code checks that the YaRN settings match the reference and raises an error for settings it does not support.
- **Recommended sampling** (from IFM's model card): `temperature=0.6`, `top_p=0.95`, and a large output budget for thinking.

## License

[Apache-2.0](https://huggingface.co/IFM/K2-Horizon-0.9B), inherited from the base model. Refer to the [original model card](https://huggingface.co/IFM/K2-Horizon-0.9B) for architecture, benchmarks and intended use. All credit for the model belongs to IFM.