AI NEWS.ccAI正在发生 未来正在更新
♡ 我的收藏 0
AI 模型库/Schiltmans/Qwen3.8-Flash-Next-Coder-cut240
MODEL PROFILE · 模型档案

Qwen3.8-Flash-Next-Coder-cut240

Schiltmans · Qwen3.8-Flash-Next-Coder-cut240

ISTA-DASLab's IQ1_M Coder GGUF of Qwen3.8-Flash-Next (ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF at 5348543e) with 768 of its 12,288 routed experts removed, served through MLX as an OpenAI-compatible endpoint for coding agents. Each layer keeps 185 to 255 of 256 routed experts, 240 on average; kept tensors are byte for byte as published. This repository is the model folder and its runner in one; the runtime is a TensorFold fork that reads the GGUF tensors in place through mlx-kquant. The fork builds on TensorFold 0.3.4 (MIT) and carries its Python engine, which upstream later replaced with a native one. `DRAFTING=off ./serve.sh` turns drafting off and keeps the disconnect and title behaviour. Some `evidence/` pages were measured with drafting off and without the disconnect and title behaviour; each says which. Requires an Apple Silicon Mac with 48 GB (for 24 GB and 32 GB Macs, see below) and macOS 26 or later (measured on an M4 Pro), about 62 GB of free disk (57 GB model files, 2.2 GB head, about 1 GB environment), git and uv (the download below uses `uvx`; `install.sh` also works with python3.11). Close memory-heavy apps first: `serve.sh` will not start if macOS reports memory pressure or has less than an estimated 36 GB free or held by cached files. This is a startup check; it does not guarantee that memory will suffice later.

译文排队中，当前展示来源原文。

文本生成codelicense:other
上下文窗口来源未披露
输入 → 输出文本 → 文本
模型权重待核验
档案更新时间2026/11/2 19:17:06
OVERVIEW

模型介绍

ISTA-DASLab's IQ1_M Coder GGUF of Qwen3.8-Flash-Next (ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF at 5348543e) with 768 of its 12,288 routed experts removed, served through MLX as an OpenAI-compatible endpoint for coding agents. Each layer keeps 185 to 255 of 256 routed experts, 240 on average; kept tensors are byte for byte as published. This repository is the model folder and its runner in one; the runtime is a TensorFold fork that reads the GGUF tensors in place through mlx-kquant. The fork builds on TensorFold 0.3.4 (MIT) and carries its Python engine, which upstream later replaced with a native one. `DRAFTING=off ./serve.sh` turns drafting off and keeps the disconnect and title behaviour. Some `evidence/` pages were measured with drafting off and without the disconnect and title behaviour; each says which. Requires an Apple Silicon Mac with 48 GB (for 24 GB and 32 GB Macs, see below) and macOS 26 or later (measured on an M4 Pro), about 62 GB of free disk (57 GB model files, 2.2 GB head, about 1 GB environment), git and uv (the download below uses `uvx`; `install.sh` also works with python3.11). Close memory-heavy apps first: `serve.sh` will not start if macOS reports memory pressure or has less than an estimated 36 GB free or held by cached files. This is a startup check; it does not guarantee that memory will suffice later.

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 · Schiltmans/Qwen3.8-Flash-Next-Coder-cut240 ↗2026/10/29 19:01:19
huggingface · enrich:ccf2b921-8dc9-4293-b031-0f51e7e045cc ↗2026/10/30 06:37:43

许可证：other。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。