CoolFace
Modelpublic

continuum-ai/qwen3.5-4b-code-forged-GGUF

sourceHugging Faceapache-2.0updated 6mo agoView on Hugging Face
6likes759downloads
Model Card

+22.7% Better at Code

Qwen3.5-4B forged for code through Experiential Plasticity.

3.04 → 2.35 perplexity · 3 cycles

<p align="center"> <a href="https://cambriantech.github.io/forge-alloy/verify/#hf.co/continuum-ai/qwen3.5-4b-code-forged-GGUF/resolve/main/qwen3.5-4b-code-forged-GGUF.alloy.json@f7f4f6ddf29019d2"> <img src="alloy-qr.png" alt="Verify Chain of Custody" width="160"/> </a> </p>

<p align="center"> <a href="https://cambriantech.github.io/forge-alloy/verify/#hf.co/continuum-ai/qwen3.5-4b-code-forged-GGUF/resolve/main/qwen3.5-4b-code-forged-GGUF.alloy.json@f7f4f6ddf29019d2"><b>Every claim on this card is verified</b></a><br> <b>Trust: self-attested</b> · 2 benchmarks · 1 device tested<br> <a href="https://github.com/CambrianTech/forge-alloy">ForgeAlloy</a> chain of custody · <a href="qwen3.5-4b-code-forged-GGUF.alloy.json">Download alloy</a> · Merkle-chained </p>


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

Benchmarks

BenchmarkResultVerified
perplexity22.7Self-reported
humanevalpendingSelf-reported

What Changed (Base → Forged)

BaseForgedDelta
Perplexity (code)3.042.35-22.7% ✅
TrainingGeneralcode, 1000 stepsLR 2e-4, 3 cycles
Pipelinetrain → quant → eval → quant3 cycles

Runs On

DeviceFormatSizeSpeed
NVIDIA GeForce RTX 5090fp16Verified
MacBook Pro 32GBfp168.0GBExpected
MacBook Air 16GBQ8_0~4.0GBExpected
MacBook Air 8GBQ4KM~2.5GBExpected
iPhone / AndroidQ4KM~2.5GBExpected

Quick Start

python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("continuum-ai/qwen3.5-4b-code-forged-GGUF",
    torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("continuum-ai/qwen3.5-4b-code-forged-GGUF")

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 GGUF quantization. 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 train → quant → eval → quant over 3 cycles on NVIDIA GeForce RTX 5090.

Chain of Custody

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

WhatProof
Model weightssha256:03dd512b17b85b9b4ee6614bc6dd46c08...
Code that ransha256:derivation-tool-o...
Forged onNVIDIA GeForce RTX 5090, 2026-04-08
Trust level`self-attested`
SpecForgeAlloy — Rust/Python/TypeScript

Make Your Own

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

<p align="center"> <a href="https://github.com/CambrianTech/continuum"><img src="https://raw.githubusercontent.com/CambrianTech/continuum/main/docs/images/factory.png" alt="Continuum Model Factory" width="400"/></a> </p>

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