Instructions to use majentik/Qwen-AgentWorld-35B-A3B-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use majentik/Qwen-AgentWorld-35B-A3B-MLX-8bit 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("majentik/Qwen-AgentWorld-35B-A3B-MLX-8bit")

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 majentik/Qwen-AgentWorld-35B-A3B-MLX-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "majentik/Qwen-AgentWorld-35B-A3B-MLX-8bit"

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": "majentik/Qwen-AgentWorld-35B-A3B-MLX-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use majentik/Qwen-AgentWorld-35B-A3B-MLX-8bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "majentik/Qwen-AgentWorld-35B-A3B-MLX-8bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "majentik/Qwen-AgentWorld-35B-A3B-MLX-8bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "majentik/Qwen-AgentWorld-35B-A3B-MLX-8bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use majentik/Qwen-AgentWorld-35B-A3B-MLX-8bit 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 "majentik/Qwen-AgentWorld-35B-A3B-MLX-8bit"

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 majentik/Qwen-AgentWorld-35B-A3B-MLX-8bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use majentik/Qwen-AgentWorld-35B-A3B-MLX-8bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "majentik/Qwen-AgentWorld-35B-A3B-MLX-8bit"

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 "majentik/Qwen-AgentWorld-35B-A3B-MLX-8bit" \
  --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"

Qwen-AgentWorld-35B-A3B-MLX-8bit

Summary

MLX 8bit (affine, 8-bit, group size 64) quantization of Qwen/Qwen-AgentWorld-35B-A3B at upstream revision 60d2b0434a53d2e62a7c00a489586815d94ebffb, converted from the BF16 safetensors with mlx_lm convert (mlx-lm 0.31.3). ~34.3 GiB on disk.

Runtime status (verified 2026-07-04): loads and generates under mlx-lm 0.31.3 — chat and code probes passed on this exact payload. Republished 2026-07-04 in the mlx-lm layout, replacing the 2026-07-02 pack, which no MLX runtime could load. Output quality beyond the smoke probes is not verified.

Runtime status

Runtime	Loads?	Notes
mlx-lm 0.31.3	✅	chat + code smoke passed per variant
mlx-vlm 0.6.3	n/a	text-only model (no vision tower)

Smoke-gated on Apple Silicon before publish (2026-07-04): this exact payload was loaded and probed per variant (pipelines/vlm_pack_smoke.py / pipelines/lm_pack_smoke.py, majek repo); verdicts in .sisyphus/evidence/lane-a-republish/ and in PROVENANCE.md.

from mlx_lm import load, generate

model, tokenizer = load("majentik/Qwen-AgentWorld-35B-A3B-MLX-8bit")
prompt = tokenizer.apply_chat_template(
    [{"role": "user", "content": "Explain KV caching in one sentence."}],
    add_generation_prompt=True, tokenize=False,
)
print(generate(model, tokenizer, prompt=prompt, max_tokens=128))

Why this variant

Affine 8-bit, group size 64 — the highest-fidelity tier, roughly half of BF16 on disk.

Reproduce

# base = snapshot of Qwen/Qwen-AgentWorld-35B-A3B @ 60d2b0434a53d2e62a7c00a489586815d94ebffb
python -m mlx_lm convert --hf-path /tmp/lane-a-republish/qwen-agentworld-35b-a3b/base --mlx-path /tmp/lane-a-republish/qwen-agentworld-35b-a3b/8bit -q --q-bits 8 --q-group-size 64 --q-mode affine

Family

All MLX variants of this model ship together:

majentik/Qwen-AgentWorld-35B-A3B-MLX-2bit
majentik/Qwen-AgentWorld-35B-A3B-MLX-3bit
majentik/Qwen-AgentWorld-35B-A3B-MLX-4bit
majentik/Qwen-AgentWorld-35B-A3B-MLX-5bit
majentik/Qwen-AgentWorld-35B-A3B-MLX-6bit
majentik/Qwen-AgentWorld-35B-A3B-MLX-8bit (this repo)
majentik/Qwen-AgentWorld-35B-A3B-MLX-MXFP4
majentik/Qwen-AgentWorld-35B-A3B-MLX-NVFP4

Provenance

Upstream: Qwen/Qwen-AgentWorld-35B-A3B @ 60d2b0434a53d2e62a7c00a489586815d94ebffb
Quantization: bits=8, mode=affine, group_size=64 (language tower only)
Toolchain: mlx 0.31.2, mlx-lm 0.31.3, mlx-vlm 0.6.3, transformers 5.12.0, huggingface_hub 1.22.0
Republished 2026-07-04 in a runtime-loadable layout; supersedes the 2026-07-02 pipelines.mlx_direct_quantize pack. Full details in PROVENANCE.md in this repo.

License + attribution

Quantized by majentik from Qwen/Qwen-AgentWorld-35B-A3B. All rights in the original model remain with its authors.

The upstream model is released under the Apache License 2.0 — see the upstream LICENSE file.

Downloads last month: 30

Safetensors

Model size

35B params

Tensor type

U32

BF16

MLX

Hardware compatibility

8-bit

Model tree for majentik/Qwen-AgentWorld-35B-A3B-MLX-8bit

Base model

Qwen/Qwen3.5-35B-A3B-Base

Finetuned

Qwen/Qwen-AgentWorld-35B-A3B

Quantized

(73)

this model