Instructions to use avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw 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("avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw")

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 avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw 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 "avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw"

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 avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw

Run Hermes

hermes

OpenClaw new

How to use avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw"

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 "avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw" \
  --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"

MLX LM

How to use avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "avlp12/Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

avlp12 commited on about 9 hours ago

Commit

f6b0c61

verified ·

1 Parent(s): 56c3da0

Withhold KL-vs-Q8 figures pending re-measurement: the 8-bit reference used as the baseline is defective (mx.split >2^31 silent corruption). Model quality and the port-parity KL~1e-7 (vs the fixed HF torch reference) are unaffected.

Browse files

Files changed (1) hide show

README.md +24 -0

README.md CHANGED Viewed

@@ -24,6 +24,30 @@ tags:
 - conversational
 ---
 # Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw · ⚠️ experimental floor build
 Apple Silicon (MLX) **mixed-precision** quantization of

 - conversational
 ---
+> [!NOTE]
+> ## 📌 KL 수치 보류 중 / KL numbers under review — the model itself is fine
+>
+> **2026-07-26.** 이 카드의 **"KL vs Q8(8bit 레퍼런스)" 수치는 현재 보류**합니다.
+> 레퍼런스로 쓰인 [8bit 빌드에 결함](https://huggingface.co/avlp12/Motif-3-Beta-Alis-MLX-8bit/discussions/1)이
+> 확인되어(`mx.split` 2³¹ 초과 텐서 침묵 손상), **손상된 레퍼런스를 기준으로 측정된 값**이기 때문입니다.
+>
+> The **"KL vs Q8" figures on this card are withheld pending re-measurement**: the 8-bit
+> build used as the reference has been found defective, so those numbers were measured
+> against a corrupted baseline.
+>
+> **보류되는 것 / withheld:** 슬라이스별 `KL vs Q8` 표 · **"DWQ가 KL을 58–72% 감소"** 주장 ·
+> `eval_ladder.png`의 KL 축
+>
+> **영향 없는 것 / unaffected — 이 빌드 자체는 정상입니다:**
+> - 모델 품질(한국어·영어·코드 생성)은 직접 생성으로 검증되었고 그대로 유효합니다.
+>   Generation quality is verified directly and stands.
+> - **포팅 패리티 `KL ≈1e-7 / token`** 은 수정된 **HF torch 레퍼런스** 기준이라 8bit와 무관하며 유효합니다.
+>   The port-parity figure is measured against the fixed HF reference, not the 8-bit build.
+> - 루프 프로브(distinct-4gram) 등 **레퍼런스가 필요 없는 측정**은 유효합니다.
+>
+> 8bit 레퍼런스를 재빌드한 뒤 재측정하여 이 카드의 수치를 갱신하고 이 주석을 내리겠습니다.
+> The reference is being rebuilt; these figures will be re-measured and this note removed.
 # Motif-3-Beta-Alis-MLX-Dynamic-2.3bpw · ⚠️ experimental floor build
 Apple Silicon (MLX) **mixed-precision** quantization of