Instructions to use OsaurusAI/Qwen-AgentWorld-35B-A3B-MXFP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsaurusAI/Qwen-AgentWorld-35B-A3B-MXFP8 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("OsaurusAI/Qwen-AgentWorld-35B-A3B-MXFP8")

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 OsaurusAI/Qwen-AgentWorld-35B-A3B-MXFP8 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/Qwen-AgentWorld-35B-A3B-MXFP8"

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": "OsaurusAI/Qwen-AgentWorld-35B-A3B-MXFP8"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use OsaurusAI/Qwen-AgentWorld-35B-A3B-MXFP8 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 "OsaurusAI/Qwen-AgentWorld-35B-A3B-MXFP8"

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 OsaurusAI/Qwen-AgentWorld-35B-A3B-MXFP8

Run Hermes

hermes

OpenClaw new

How to use OsaurusAI/Qwen-AgentWorld-35B-A3B-MXFP8 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/Qwen-AgentWorld-35B-A3B-MXFP8"

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 "OsaurusAI/Qwen-AgentWorld-35B-A3B-MXFP8" \
  --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 OsaurusAI/Qwen-AgentWorld-35B-A3B-MXFP8 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "OsaurusAI/Qwen-AgentWorld-35B-A3B-MXFP8"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "OsaurusAI/Qwen-AgentWorld-35B-A3B-MXFP8"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "OsaurusAI/Qwen-AgentWorld-35B-A3B-MXFP8",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Qwen-AgentWorld-35B-A3B · MXFP8

Official OsaurusAI MXFP8 build of Qwen/Qwen-AgentWorld-35B-A3B (Apache-2.0) — a ~35B-total / ~3B-active hybrid MoE (qwen3_5_moe). Near-lossless 8-bit microscaled FP; runs on Apple Silicon via Osaurus / mlx_lm.

~33 GB bundle (down from ~65 GB bf16).
MXFP8: microscaled FP8 (group-size 32) across the weights, high-precision embeddings/head. Use this for the highest fidelity; use JANG_4M (~17.6 GB) for the smallest footprint.
Text-only. The upstream checkpoint ships a vestigial vision_config with no vision-tower weights, so this bundle is correctly stamped modality: text (has_vision: false).

Reasoning behavior. This model shows its work ("Thinking Process: …") by default. The soft /no_think suppression switch is not reliable on this MXFP8 pack — for deterministic reasoning-off, prefer the JANG_4M pack, which honors it.

Architecture


Family	`qwen3_5_moe` (hybrid)
Layers	40 — 30 linear-attention (Gated DeltaNet / SSM) + 10 full-attention (1 every 4)
Experts	256 routed (8 active)
Active params	~3 B
Cache	hybrid (recurrent GDN state + KV for full-attn layers)

The Gated-DeltaNet layers (conv1d / A_log / dt_bias / gated in_proj_{qkv,a,b,z}) carry a recurrent state across the full-attention layers — verified coherent with long-context recall in the Osaurus (vMLX-Swift) runtime.

Usage

python -m mlx_lm generate --model OsaurusAI/Qwen-AgentWorld-35B-A3B-MXFP8 --prompt "Explain a hash map in two sentences."

Or load in Osaurus for a local agent loop (tool-calling supported via the qwen tool parser).

Provenance

Quantization: Osaurus · MXFP8 (microscaled FP8, group-size 32) · eric@osaurus.ai

Downloads last month: 518

Safetensors

Model size

10B params

Tensor type

U32

F16

MLX

Hardware compatibility

Quantized

Model tree for OsaurusAI/Qwen-AgentWorld-35B-A3B-MXFP8

Base model

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

Finetuned

Qwen/Qwen-AgentWorld-35B-A3B

Finetuned

(7)

this model