What are the hardware requirements for Qwen3.5 4B Code Forged?

Qwen3.5 4B Code Forged requires approximately 8.4 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.5 4B Code Forged and how large is it?

Qwen3.5 4B Code Forged is developed by continuum-ai, a model with 4b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Qwen3.5 4B Code Forged?

Qwen3.5 4B Code Forged is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.5 4B Code Forged by continuum-ai — VRAM 8.4GB, 256K context

Name: Qwen3.5 4B Code Forged
Author: continuum-ai

Qwen3.5 4B Code Forged is an open-source language model by continuum-ai. Features: 4b LLM, VRAM: 8.4GB, Context: 256K, License: apache-2.0, Quantized, LLM Explorer Score: 0.23.

4b Agentic-coding Android Apple-silicon Attested Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-4b Bash C Chain-of-custody Chinese Code Code-completion Code-generation Code-infill Codegen Coder Coding Consumer-gpu Cpp Cryptographically-verified Css Delta-forge Edge-inference Embedded English Forge-alloy Function-calling Ggml Gguf Go Html Iphone Java Javascript Kotlin Llama-cpp Lm-studio Local-inference Macbook Mlx Mobile Multilingual Ollama On-device Php Python Q4 Q4-k-m Quantized Qwen Qwen3 Qwen3.5 Qwen3 5 text Raspberry-pi Region:us Reproducible Ruby Rust Safetensors Software-engineering Sql Swift Typescript

Model Card on HF 🤗: https://huggingface.co/continuum-ai/qwen3.5-4b-code-forged

Qwen3.5 4B Code Forged Parameters and Internals

LLM Name	Qwen3.5 4B Code Forged
Repository 🤗	https://huggingface.co/continuum-ai/qwen3.5-4b-code-forged
Base Model(s)	Qwen/Qwen3.5-4B Qwen/Qwen3.5-4B
Model Size	4b
Required VRAM	8.4 GB
Updated	2026-08-01
Maintainer	continuum-ai
Model Type	qwen3_5_text
Model Files	8.4 GB
Supported Languages	en zh
Quantization Type	q4
Model Architecture	Qwen3_5ForCausalLM
License	apache-2.0
Context Length	262144
Model Max Length	262144
Transformers Version	5.3.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Vocabulary Size	248320
Errors	replace

Rank the Qwen3.5 4B Code Forged capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Qwen3.5 4B Code Forged

Best Alternatives	Context / RAM	Downloads	Likes
NeoHorse 1 4B 4bit	256K / 2.4 GB	118	2
Qwen3.5 Text 4B Bnb 4bit	256K / 3.1 GB	2125	2
Qwen3.5 4B Qat Lean 4bit Mlx	256K / 2.4 GB	155	0
Agents A1 4B Fable Preview	256K / 8.4 GB	103	0
Decider 4B	256K / 8.4 GB	23565	17
NeoHorse 1 4B	256K / 8.4 GB	1771	179
JevK5	256K / 8.4 GB	5525	13
Wald 4B	256K / 8.4 GB	4394	8
Plumb 4B	256K / 8.4 GB	2825	6
JSBAI Coder 4B	256K / 8.4 GB	2795	1

Note: green Score (e.g. "73.2") means that the model is better than continuum-ai/qwen3.5-4b-code-forged.