Instructions to use barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use barozp/Qwen3.8-Whittle-MoE-27B-MLX-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("barozp/Qwen3.8-Whittle-MoE-27B-MLX-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 barozp/Qwen3.8-Whittle-MoE-27B-MLX-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 "barozp/Qwen3.8-Whittle-MoE-27B-MLX-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": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use barozp/Qwen3.8-Whittle-MoE-27B-MLX-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 "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use barozp/Qwen3.8-Whittle-MoE-27B-MLX-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 "barozp/Qwen3.8-Whittle-MoE-27B-MLX-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 barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use barozp/Qwen3.8-Whittle-MoE-27B-MLX-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 "barozp/Qwen3.8-Whittle-MoE-27B-MLX-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 "barozp/Qwen3.8-Whittle-MoE-27B-MLX-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"

Qwen3.8-Whittle-MoE-27B-MLX-4bit

MLX 4-bit conversion of logic65/Qwen3.8-Whittle-MoE-27B-A17.8B -- a post-hoc MoE carved from Qwen/Qwen3.8-27B (64 routed expert slivers + 1 shared expert per layer, top-16 routing, 17.8B active of 27B total, router-healed + anti-loop trained, v2.1) -- for Apple Silicon. Sibling formats:

bf16 safetensors source (v2.1): logic65/Qwen3.8-Whittle-MoE-27B-A17.8B
GGUF quantizations: logic65/Qwen3.8-Whittle-MoE-27B-A17.8B-GGUF

Converted straight from the v2.1 bf16 safetensors weights (not from any GGUF quant). Note: the source ships without an MTP head (mtp_layers: 0) -- this MLX build is autoregressive only; MTPLX speculative decoding does not apply.

Conversion details

Bits: 4 (group_size=64, affine)
Command: python -m mlx_lm.convert --hf-path logic65/Qwen3.8-Whittle-MoE-27B-A17.8B --mlx-path <out> --quantize --q-bits 4 --q-group-size 64
Tooling: mlx 0.32.1 · mlx-lm 0.31.3 · hub 1.27.0; source commit 08741134dbc3
Converter: mlx-lm
Environment: Google Colab G4 (RTX PRO 6000 Blackwell 96 GB), MLX cuda12 backend
Full conversion log ships in this repo as conversion_log.txt

Usage

pip install -U mlx-lm

# text-only chat
python -m mlx_lm.generate \
  --model barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit \
  --prompt "Explain the Monty Hall problem briefly." \
  --max-tokens 512

# OpenAI-compatible local server
python -m mlx_lm.server \
  --model barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit

About the source model

A post-hoc MoE carved from Qwen3.8-27B: each layer's dense FFN (17408) was partitioned into 64 routed expert slivers of width 192 + one shared expert of width 5120; a small router picks 16 of 64 slivers per token (17.8B active / 27B total). Freshly carved it scored 4/39 on the knowledge battery; training only the 64 routers recovered 27/39. The v2.1 lineage adds anti-loop training (245 complete teacher answers with top-32 logprobs) and a balancing epoch: single-turn loop rate 8% (from 69%), structured-output failures 22% (from ~75%), knowledge battery 28/39. Full method and failure log: WHITTLE_FINDINGS.md.

Source chain

Qwen/Qwen3.8-27B (dense base) -> logic65/Qwen3.8-Whittle-MoE-27B-A17.8B (post-hoc MoE carve + router healing + v2.1 anti-loop) -> this repo (MLX 4-bit conversion)

Downloads last month: 2,258

Safetensors

Model size

27B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit

Base model

Qwen/Qwen3.8-27B

Finetuned

logic65/Qwen3.8-Whittle-MoE-27B-A17.8B

Quantized

(4)

this model