Instructions to use continuum-ai/qwen3.5-4b-code-128k-forged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use continuum-ai/qwen3.5-4b-code-128k-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/qwen3.5-4b-code-128k-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
LM Studio

Pi new

How to use continuum-ai/qwen3.5-4b-code-128k-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/qwen3.5-4b-code-128k-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/qwen3.5-4b-code-128k-forged"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use continuum-ai/qwen3.5-4b-code-128k-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/qwen3.5-4b-code-128k-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/qwen3.5-4b-code-128k-forged

Run Hermes

hermes

MLX LM

How to use continuum-ai/qwen3.5-4b-code-128k-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/qwen3.5-4b-code-128k-forged"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "continuum-ai/qwen3.5-4b-code-128k-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/qwen3.5-4b-code-128k-forged",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

32K → 128K: Context Window Extended 4x

We took Qwen3.5-4B (32K context) and extended it to 128K context via YaRN RoPE scaling — then trained it on code for 3 cycles to recover and improve quality.

Paste your entire codebase, not just one file.

Every claim on this card is verified
Trust: self-attested · 3 benchmarks · 1 device tested
ForgeAlloy chain of custody · Download alloy · Merkle-chained

Qwen3.5-4B with cryptographic provenance via the ForgeAlloy chain of custody.

Benchmarks

Benchmark	Result	Verified
perplexity	18.7	Self-reported
humaneval	32.3	Self-reported
humaneval+	28.0	Self-reported

What Changed (Base → Forged)

	Base	Forged	Delta
Perplexity (code)	3.04	2.47	-18.7% ✅
Context Window	32,768	131,072	4x via yarn ✅
Training	General	code, 2000 steps	LR 2e-4, 3 cycles
Pipeline		context-extend → train	3 cycles

Runs On

Device	Format	Size	Speed
RTX 5090	fp16	8.4GB	~23 tok/s (verified)
MacBook Pro 32GB	fp16	8.4GB	Expected
MacBook Air 16GB	Q8_0	~4.2GB	Expected
MacBook Air 8GB	Q4_K_M	~2.6GB	Expected
iPhone / Android	Q4_K_M	~2.6GB	Expected

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("continuum-ai/qwen3.5-4b-code-128k-forged",
    torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("continuum-ai/qwen3.5-4b-code-128k-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 YaRN context extension. 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 context-extend → train over 3 cycles on RTX 5090.

Chain of Custody

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

What	Proof
Model weights	`sha256:fef00899cd644c6118c9fc63d1f1e6b63...`
Code that ran	`sha256:8a421f10994ecb1b5...`
Git commit	`a6b200cb465e`
Forged on	RTX 5090, 2026-04-02T02:38:44-0500
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