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

Libraries

How to use continuum-ai/qwen3.5-4b-code-forged-GGUF with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm
# if on a CUDA device, also pip install mlx[cuda]

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("continuum-ai/qwen3.5-4b-code-forged-GGUF")

prompt = "Once upon a time in"
text = generate(model, tokenizer, prompt=prompt, verbose=True)

llama-cpp-python

How to use continuum-ai/qwen3.5-4b-code-forged-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="continuum-ai/qwen3.5-4b-code-forged-GGUF",
	filename="qwen3.5-4b-code-forged-Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use continuum-ai/qwen3.5-4b-code-forged-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf continuum-ai/qwen3.5-4b-code-forged-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf continuum-ai/qwen3.5-4b-code-forged-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf continuum-ai/qwen3.5-4b-code-forged-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf continuum-ai/qwen3.5-4b-code-forged-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf continuum-ai/qwen3.5-4b-code-forged-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf continuum-ai/qwen3.5-4b-code-forged-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf continuum-ai/qwen3.5-4b-code-forged-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf continuum-ai/qwen3.5-4b-code-forged-GGUF:Q4_K_M

Use Docker

docker model run hf.co/continuum-ai/qwen3.5-4b-code-forged-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use continuum-ai/qwen3.5-4b-code-forged-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "continuum-ai/qwen3.5-4b-code-forged-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "continuum-ai/qwen3.5-4b-code-forged-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/continuum-ai/qwen3.5-4b-code-forged-GGUF:Q4_K_M

Ollama
How to use continuum-ai/qwen3.5-4b-code-forged-GGUF with Ollama:
```
ollama run hf.co/continuum-ai/qwen3.5-4b-code-forged-GGUF:Q4_K_M
```

Unsloth Studio

How to use continuum-ai/qwen3.5-4b-code-forged-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for continuum-ai/qwen3.5-4b-code-forged-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for continuum-ai/qwen3.5-4b-code-forged-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for continuum-ai/qwen3.5-4b-code-forged-GGUF to start chatting

Atomic Chat new

MLX LM

How to use continuum-ai/qwen3.5-4b-code-forged-GGUF with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Generate some text
mlx_lm.generate --model "continuum-ai/qwen3.5-4b-code-forged-GGUF" --prompt "Once upon a time"

Docker Model Runner
How to use continuum-ai/qwen3.5-4b-code-forged-GGUF with Docker Model Runner:
```
docker model run hf.co/continuum-ai/qwen3.5-4b-code-forged-GGUF:Q4_K_M
```

Lemonade

How to use continuum-ai/qwen3.5-4b-code-forged-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull continuum-ai/qwen3.5-4b-code-forged-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.qwen3.5-4b-code-forged-GGUF-Q4_K_M

List all available models

lemonade list

qwen3.5-4b-code-forged-GGUF / qwen3.5-4b-code-forged-GGUF.alloy.json

EnricoFermi

Correct qwen3.5-4b-code-forged-GGUF.alloy.json pass@1 to canonical evalplus convention (v1.0.0)

56b1bd6 verified 2 months ago

raw

history blame contribute delete

3.48 kB

	{
	"name": "qwen3.5-4b-code-forged-GGUF",
	"version": "1.0.0",
	"description": "GGUF derivative of [`qwen3.5-4b-code-forged`](https://huggingface.co/continuum-ai/qwen3.5-4b-code-forged). Same forge journey as the parent (prune + train as published in the parent's alloy); this artifact adds a single 'gguf' transformation stage to produce a smaller / faster / more-portable variant of the same logical model. Inherits the parent's published benchmark results; per-variant evaluation samples will land in a follow-up release if/when per-variant benchmarks are run.",
	"author": "continuum-ai",
	"tags": [
	"derivative",
	"delta-forge",
	"alloy-backfilled",
	"gguf",
	"forge-alloy"
	],
	"license": "apache-2.0",
	"source": {
	"baseModel": "Qwen/Qwen3.5-4B",
	"architecture": "qwen3_5",
	"isMoE": false
	},
	"stages": [
	{
	"type": "train",
	"domain": "code",
	"steps": 1000,
	"learningRate": "2e-4"
	},
	{
	"type": "quant",
	"format": "gguf",
	"quantTypes": [
	"Q4_K_M"
	],
	"deviceTargets": []
	},
	{
	"type": "eval",
	"benchmarks": [
	{
	"name": "humaneval"
	}
	],
	"compareToBase": true
	},
	{
	"type": "quant",
	"format": "gguf",
	"quantTypes": [
	"Q4_K_M",
	"Q8_0"
	],
	"deviceTargets": [
	"macbook-pro-m-series",
	"macbook-air-16gb",
	"rtx3060",
	"rtx4070",
	"rtx4090",
	"iphone",
	"android"
	],
	"notes": "GGUF quantization of the parent's safetensors weights via llama.cpp llama-quantize. Targets llama.cpp / Ollama / LM Studio / koboldcpp inference runtimes. Q4_K_M and Q8_0 shipped together so users can pick the size/quality tier their hardware supports."
	}
	],
	"cycles": 3,
	"derivedFrom": {
	"repo": "continuum-ai/qwen3.5-4b-code-forged",
	"alloyHash": null,
	"kind": "gguf"
	},
	"results": {
	"completedAt": "2026-03-31T12:13:43-0500",
	"baselinePerplexity": 3.0382,
	"finalPerplexity": 2.3487,
	"improvementPct": 22.7,
	"benchmarks": [
	{
	"name": "perplexity",
	"metrics": {
	"baseline": 3.0382,
	"final": 2.3487,
	"improvement": 22.7
	}
	},
	{
	"name": "humaneval",
	"subset": null,
	"metrics": {
	"status": "pending"
	},
	"submittedToLeaderboard": false
	}
	],
	"hardwareVerified": [
	{
	"device": "NVIDIA GeForce RTX 5090",
	"format": "fp16",
	"verified": true
	}
	],
	"samples": [],
	"integrity": {
	"trustLevel": "self-attested",
	"code": {
	"runner": "sentinel-ai/derive_alloy_from_parent (gguf)",
	"version": "1.0",
	"binaryHash": "sha256:derivation-tool-only"
	},
	"modelHash": "sha256:03dd512b17b85b9b4ee6614bc6dd46c08d0bc8e07b92f01b2934540e4f5cbb96",
	"fileHashes": [
	{
	"filename": "qwen3.5-4b-code-forged-Q4_K_M.gguf",
	"sha256": "15c8ebc22ac16e3e922041f25d285f8a322e228196de0e9b12592b8bf8b7646e",
	"size": 2708797184
	},
	{
	"filename": "qwen3.5-4b-code-forged-Q8_0.gguf",
	"sha256": "c56465451bef33353a1f075d670d07bb11c11f60d4463c6bd4fb24f6155acd40",
	"size": 4482395904
	}
	],
	"datasets": [],
	"attestedAt": "2026-04-08",
	"parentAlloyHash": null
	}
	}
	}