Instructions to use continuum-ai/qwen3.5-27b-code-forged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use continuum-ai/qwen3.5-27b-code-forged 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("continuum-ai/qwen3.5-27b-code-forged")

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 continuum-ai/qwen3.5-27b-code-forged with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "continuum-ai/qwen3.5-27b-code-forged"

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": "continuum-ai/qwen3.5-27b-code-forged"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use continuum-ai/qwen3.5-27b-code-forged with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "continuum-ai/qwen3.5-27b-code-forged"

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 "continuum-ai/qwen3.5-27b-code-forged" \
  --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 continuum-ai/qwen3.5-27b-code-forged with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "continuum-ai/qwen3.5-27b-code-forged"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "continuum-ai/qwen3.5-27b-code-forged"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "continuum-ai/qwen3.5-27b-code-forged",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use continuum-ai/qwen3.5-27b-code-forged 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 "continuum-ai/qwen3.5-27b-code-forged"

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 continuum-ai/qwen3.5-27b-code-forged

Run Hermes

hermes

Atomic Chat

qwen3.5-27b-code-forged / README.md

EnricoFermi

fix: use hf.co (CORS-open) in verify URLs

1e48987 verified 4 months ago

preview code

Raw

History Blame Contribute Delete

5 kB

metadata

tags:
  - 27b
  - agentic-coding
  - alloy-backfilled
  - android
  - apple-silicon
  - attested
  - bash
  - c
  - chain-of-custody
  - chinese
  - code
  - code-completion
  - code-generation
  - code-infill
  - coder
  - coding
  - compacted
  - consumer-gpu
  - cpp
  - cryptographically-verified
  - css
  - edge-inference
  - efficient
  - embedded
  - english
  - forge-alloy
  - function-calling
  - go
  - head-pruning
  - html
  - iphone
  - java
  - javascript
  - kotlin
  - llama-cpp
  - lm-studio
  - local-inference
  - macbook
  - mlx
  - mobile
  - multilingual
  - ollama
  - on-device
  - optimized
  - php
  - programming
  - pruned
  - python
  - qwen
  - qwen3
  - qwen3.5
  - raspberry-pi
  - reproducible
  - ruby
  - rust
  - software-engineering
  - sql
  - swift
  - text-generation
  - typescript
base_model: Qwen/Qwen3.5-27B
pipeline_tag: text-generation
license: apache-2.0

30% Smaller, +3.5% Better

Qwen3.5-27B pruned by 30% and retrained for code through Experiential Plasticity.

3.07 → 2.96 perplexity · 2 cycles

Every claim on this card is verified
Trust: self-attested · 1 benchmark · 2 devices tested
ForgeAlloy chain of custody · Download alloy · Merkle-chained

Qwen3.5-27B with cryptographic provenance via the ForgeAlloy chain of custody.

Benchmarks

Benchmark	Result	Verified
perplexity	3.0	Self-reported

What Changed (Base → Forged)

	Base	Forged	Delta
Perplexity (code)	3.07	2.96	-3.5% ✅
Pruning	None	30% heads (magnitude)	-30% params ✅
Training	General	code, 500 steps	LR 2e-4, 2 cycles
Pipeline		prune → train	2 cycles

Runs On

Device	Format	Size	Speed
MacBook Pro 32GB	fp16	—	Verified
RTX 3090 24GB	fp16	—	Verified
MacBook Pro 32GB	fp16	8.0GB	Expected
MacBook Air 16GB	Q8_0	~4.0GB	Expected
MacBook Air 8GB	Q4_K_M	~2.5GB	Expected
iPhone / Android	Q4_K_M	~2.5GB	Expected

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("continuum-ai/qwen3.5-27b-code-forged",
    torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("continuum-ai/qwen3.5-27b-code-forged")

inputs = tokenizer("def merge_sort(arr):", return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(output[0], skip_special_tokens=True))

Methodology

Produced via head pruning. Full methodology, ablations, and per-stage rationale are in the methodology paper and the companion MODEL_METHODOLOGY.md in this repository. The pipeline ran as prune → train over 2 cycles on MacBook Pro 32GB.

Chain of Custody

Scan the QR or verify online. Download the alloy file to verify independently.

What	Proof
Model weights	`sha256:4b4c056e252719d09fffd65c7a72aba3a...`
Code that ran	`sha256:legacy-pre-alloy-...`
Forged on	MacBook Pro 32GB, 2026-03-27T20:29:26-0500
Trust level	`self-attested`
Spec	ForgeAlloy — Rust/Python/TypeScript

Make Your Own

Forged with Continuum — a distributed AI world that runs on your hardware.

The Factory configurator lets you design and forge custom models visually — context extension, pruning, LoRA, quantization, vision/audio modalities. Pick your target devices, the system figures out what fits.

GitHub · All Models · Forge-Alloy

License

apache-2.0