AI NEWS.ccAI正在发生 未来正在更新
♡ 我的收藏 0
AI 模型库/jica98/qwen3.5-4B-super-coder
MODEL PROFILE · 模型档案

qwen3.5-4B-super-coder

jica98 · qwen3.5-4B-super-coder

`qwen3.5-4B-super-coder` is a 4-bit quantized GGUF model optimized for fast, reliable coding, structured tool calling, and active reasoning (thinking mode) on consumer/mobile hardware. It is distilled from Claude Sonnet 4.6 & Opus 4.6, and merged/quantized using Unsloth. - **Base Model**: `Qwen/Qwen3.5-4B` - **Format**: GGUF (Q_4.0 Quantization) - **Size**: ~2.6 GB - **Context Window**: 32K (optimized for mobile RAM budgets, natively supports up to 262K/1M context via YaRN) - **Key Architectural Advantage**: The base `Qwen3.5-4B` model uses a hybrid architecture combining **Gated DeltaNet** (3 layers) and **Full Attention** (1 layer) repeating. Since only 8 of the 32 layers store a full KV cache, the KV cache footprint is incredibly small (~0.4GB for 32K context), making it exceptionally well-suited for high-context coding on mobile devices (e.g., iPhone 15 Pro+, flagship Android, iPad Pro). This model was trained using a staged Supervised Fine-Tuning (SFT) pipeline to systematically inject reasoning capability, coding specialization, and tool-calling precision:

译文排队中，当前展示来源原文。

文本生成
上下文窗口32,768 Token
输入 → 输出文本 → 文本
模型权重待核验
档案更新时间2026/11/2 19:16:04
OVERVIEW

模型介绍

`qwen3.5-4B-super-coder` is a 4-bit quantized GGUF model optimized for fast, reliable coding, structured tool calling, and active reasoning (thinking mode) on consumer/mobile hardware. It is distilled from Claude Sonnet 4.6 & Opus 4.6, and merged/quantized using Unsloth. - **Base Model**: `Qwen/Qwen3.5-4B` - **Format**: GGUF (Q_4.0 Quantization) - **Size**: ~2.6 GB - **Context Window**: 32K (optimized for mobile RAM budgets, natively supports up to 262K/1M context via YaRN) - **Key Architectural Advantage**: The base `Qwen3.5-4B` model uses a hybrid architecture combining **Gated DeltaNet** (3 layers) and **Full Attention** (1 layer) repeating. Since only 8 of the 32 layers store a full KV cache, the KV cache footprint is incredibly small (~0.4GB for 32K context), making it exceptionally well-suited for high-context coding on mobile devices (e.g., iPhone 15 Pro+, flagship Android, iPad Pro). This model was trained using a staged Supervised Fine-Tuning (SFT) pipeline to systematically inject reasoning capability, coding specialization, and tool-calling precision:

主要特点

特点摘要待依据来源补齐，不凭模型名称推断能力。

局限与注意事项

暂无足够来源支持具体缺点结论。请重点验证实际任务表现、时延、数据政策、许可与版本生命周期。

PRICING & COST

来源报价与费用分析

同一模型在不同渠道、地区和配置下可能采用不同价格。下表独立保留各渠道报价，不将渠道价格视为厂商官方统一价格。

来源 / 渠道输入输出计费单位采集时间
暂未取得可核验报价，请查阅来源渠道。

按月估算基础 Token 费用

—

预估不包含缓存优惠、阶梯定价、多模态附加费用、网络检索、税费及推理额外输出。

INDEPENDENT BENCHMARKS

公开评测与运行配置

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

查看完整已收录榜单 →

常见问题

开放权重是否代表可以免费商用？

不一定。应核对具体版本许可证、商用门槛和使用政策。自部署还会产生算力和维护成本。

这些价格是实时结算价格吗？

不是实时结算价格，而是带采集时间的来源报价快照。请到对应渠道核对当前版本、区域、折扣和计费方式。

资料来源与可追溯记录

huggingface · jica98/qwen3.5-4B-super-coder ↗2026/10/31 21:24:32
huggingface · enrich:61cf272d-6f63-44b9-91ee-bea4a3fe3173 ↗2026/10/29 18:48:10

许可证：来源未披露，须进一步核验。模型介绍与第三方评测均以原来源的具体版本和方法为准。