Instructions to use mlx-community/K2-Horizon-7B-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/K2-Horizon-7B-4bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/K2-Horizon-7B-4bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use mlx-community/K2-Horizon-7B-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/K2-Horizon-7B-4bit"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mlx-community/K2-Horizon-7B-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use mlx-community/K2-Horizon-7B-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/K2-Horizon-7B-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/K2-Horizon-7B-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/K2-Horizon-7B-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use mlx-community/K2-Horizon-7B-4bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/K2-Horizon-7B-4bit"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default mlx-community/K2-Horizon-7B-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mlx-community/K2-Horizon-7B-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/K2-Horizon-7B-4bit"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "mlx-community/K2-Horizon-7B-4bit" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

K2-Horizon-7B-4bit / README.md

Jianshu001

Update model card for the mlx-community namespace

c869837 verified 10 days ago

preview code

Raw History Blame Contribute Delete

5.81 kB

metadata

license: apache-2.0
license_link: https://huggingface.co/IFM/K2-Horizon-7B
base_model: IFM/K2-Horizon-7B
base_model_relation: quantized
library_name: mlx
pipeline_tag: text-generation
tags:
  - mlx
  - quantized
  - dense
  - k2-horizon

K2-Horizon-7B (MLX, 4-bit)

Mixed-precision 4-bit MLX quantization of IFM/K2-Horizon-7B, converted from revision f846b1e. 6.4 bits/weight effective, 7.2 GB on disk. For Apple silicon.

K2-Horizon-7B is IFM's medium dense K2-Horizon model: a 7B decoder-only model with a 512K (524,288-token) context window.

Requirements

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

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

Mixed precision, chosen from measurements rather than a fixed rule (integer affine quantization, bf16 scales and biases):

4-bit, group size 32: the MLP weights (gate_proj, up_proj, down_proj). These hold most of the parameters.
8-bit, group size 64: everything else: attention, the embeddings and lm_head.

Plain 4-bit (everything 4-bit, group size 64) loses too much on this model: +18.6% WikiText-2 perplexity versus bf16. This recipe loses +4.5%. On all three dense K2-Horizon models, plain 4-bit lost 18-22%, far more than on the 36B MoE model, so the dense 4-bit repos use this mixed recipe.

Memory

Peak 7.3 GB for a short prompt; fits a 16 GB Mac. The KV cache adds about 144 KB per token in bf16 (18.0 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 36 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 (256/256 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: 69.0 tok/s generation, peak 7.3 GB (short prompt).

Benchmarks (all K2-Horizon-7B 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	8-bit	4-bit
Bits/weight	16	8.5	6.4
Disk	18.0 GB	9.6 GB	7.2 GB
Peak memory	18.1 GB	9.7 GB	7.3 GB
WikiText-2 perplexity	14.738	14.762 (+0.2%)	15.395 (+4.5%)
Generation	29.3 tok/s	52.5 tok/s	69.0 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.

Usage

mlx_lm.generate --model mlx-community/K2-Horizon-7B-4bit --trust-remote-code --prompt "Explain mixture-of-experts in two sentences." --max-tokens 2048

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-7B-4bit").
model, tokenizer = load("mlx-community/K2-Horizon-7B-4bit", 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.
Chat template change: the original template raises an error when an earlier assistant message has no thinking field, which is what OpenAI-style clients send. The template here renders empty thinking for those messages instead. Nothing else was changed.

License

Apache-2.0, inherited from the base model. Refer to the original model card for architecture, benchmarks and intended use. All credit for the model belongs to IFM.