Instructions to use nom666/Qwopus3.6-27B-v2-MTPLX-4bit-Speed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nom666/Qwopus3.6-27B-v2-MTPLX-4bit-Speed 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("nom666/Qwopus3.6-27B-v2-MTPLX-4bit-Speed")

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 nom666/Qwopus3.6-27B-v2-MTPLX-4bit-Speed with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nom666/Qwopus3.6-27B-v2-MTPLX-4bit-Speed"

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": "nom666/Qwopus3.6-27B-v2-MTPLX-4bit-Speed"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use nom666/Qwopus3.6-27B-v2-MTPLX-4bit-Speed 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 "nom666/Qwopus3.6-27B-v2-MTPLX-4bit-Speed"

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 nom666/Qwopus3.6-27B-v2-MTPLX-4bit-Speed

Run Hermes

hermes

MLX LM

How to use nom666/Qwopus3.6-27B-v2-MTPLX-4bit-Speed with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "nom666/Qwopus3.6-27B-v2-MTPLX-4bit-Speed"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "nom666/Qwopus3.6-27B-v2-MTPLX-4bit-Speed"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "nom666/Qwopus3.6-27B-v2-MTPLX-4bit-Speed",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Qwopus3.6-27B-v2 · MTPLX 4-bit Speed

The speed-focused MTPLX build of Qwopus3.6-27B-v2 — native multi-token-prediction speculative decoding on Apple Silicon, no external drafter, exact rejection sampling, so sampling behaves exactly like normal decoding, just faster. Higher-precision sibling: nom666/Qwopus3.6-27B-v2-MTPLX-8bit-Quality.

Forged with mtplx forge build from the original BF16 Jackrong/Qwopus3.6-27B-v2:

Body: flat 4-bit MLX affine quantization, group size 64
MTP head: preserved in BF16 (mtp_policy: keep_bf16), packed as mtp.safetensors sidecar
Size: ~15 GB (runs comfortably on 24 GB Macs at moderate context; 32 GB+ for long context)
Calibrated MTP contract included (mtplx_runtime.json)

Measured performance (Apple M5 Max, 128 GB, MTPLX 1.0.3)

Build	Decode	Acceptance by depth
This (4-bit, MTP depth 3)	54.8 tok/s	93% / 81% / 77%
8-bit Quality sibling (MTP depth 3)	39.0 tok/s	94% / 86% / 74%

Verification suite: long-code-uncapped, 2048-token budget. For reference, Qwopus-v2 Q6_K on llama.cpp with MTP (n=2) does ~24–26 tok/s on the same machine.

Usage

brew install youssofal/mtplx/mtplx   # or pipx install mtplx
mtplx pull nom666/Qwopus3.6-27B-v2-MTPLX-4bit-Speed
mtplx quickstart --model nom666/Qwopus3.6-27B-v2-MTPLX-4bit-Speed \
  --depth 3 --paged-kv-quantization q8 --batching-preset agent --reasoning off

Serves OpenAI-compatible (/v1/chat/completions) and Anthropic-compatible (/v1/messages) endpoints with warm-prefix KV reuse, SSD session cache, continuous batching, and vision support. Full 262144-token context; only 16 of 64 layers carry KV (hybrid Gated DeltaNet architecture), so KV at 256K is ~16 GiB BF16 / ~8 GiB q8.

Notes

Runtime contract tier is forge-local: verified on the forging machine (M5 Max). MTPLX loads it with an honest provenance note.
Prefer the 8-bit Quality sibling for maximum-fidelity agentic coding; this 4-bit build is the throughput pick.
Quantized with MTPLX 1.0.3 Forge. All credit for the fine-tune to Jackrong; base model Qwen3.6-27B (Apache-2.0).

Downloads last month: 219

Safetensors

Model size

27B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for nom666/Qwopus3.6-27B-v2-MTPLX-4bit-Speed

Base model

Jackrong/Qwopus3.6-27B-v2

Quantized

(55)

this model