AI NEWS.ccAI正在发生 未来正在更新
♡ 我的收藏 0
AI 模型库/chtisgit/Qwen3.6-35B-A3B-2Bit-GSQ-hybrid-GGUF
MODEL PROFILE · 模型档案

Qwen3.6-35B-A3B-2Bit-GSQ-hybrid-GGUF

chtisgit · Qwen3.6-35B-A3B-2Bit-GSQ-hybrid-GGUF

> **On NVIDIA GPUs, use llama.cpp b11390 (4 October 2026) or newer.** Older > CUDA builds crash on prompts of certain lengths (230, 344 and 457 tokens > in our tests) with "CUDA error: an illegal memory access was encountered". > Other lengths work normally, and CPU-only builds are not affected. > Upstream fix: #29941. This is a GGUF conversion of `ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ`. It is essentially the DASLab GSQ checkpoint repackaged into stock llama.cpp types, with the small conversion errors documented below. It is not a new quantization, fine-tune, or model release. It is distributed as a text-model GGUF plus a separate BF16/F32 vision-projector GGUF. The routed experts use Q2_0 (source: 2-bit GSQ), while attention, linear attention, shared-expert, and LM-head weights use Q8_0 (source: INT8). Remaining text-model tensors use BF16 or F32 (source: BF16) as required by llama.cpp's canonical `QWEN35MOE` layout. The companion projector retains the source BF16 vision tower as BF16 or exact F32 promotions. MTP weights remain omitted.

译文排队中，当前展示来源原文。

视觉问答license:apache-2.0
上下文窗口来源未披露
输入 → 输出文本、图像 → 文本
模型权重待核验
档案更新时间2026/11/2 19:15:51
OVERVIEW

模型介绍

> **On NVIDIA GPUs, use llama.cpp b11390 (4 October 2026) or newer.** Older > CUDA builds crash on prompts of certain lengths (230, 344 and 457 tokens > in our tests) with "CUDA error: an illegal memory access was encountered". > Other lengths work normally, and CPU-only builds are not affected. > Upstream fix: #29941. This is a GGUF conversion of `ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ`. It is essentially the DASLab GSQ checkpoint repackaged into stock llama.cpp types, with the small conversion errors documented below. It is not a new quantization, fine-tune, or model release. It is distributed as a text-model GGUF plus a separate BF16/F32 vision-projector GGUF. The routed experts use Q2_0 (source: 2-bit GSQ), while attention, linear attention, shared-expert, and LM-head weights use Q8_0 (source: INT8). Remaining text-model tensors use BF16 or F32 (source: BF16) as required by llama.cpp's canonical `QWEN35MOE` layout. The companion projector retains the source BF16 vision tower as BF16 or exact F32 promotions. MTP weights remain omitted.

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 · chtisgit/Qwen3.6-35B-A3B-2Bit-GSQ-hybrid-GGUF ↗2026/10/29 21:12:34
huggingface · enrich:3fde76c4-81b4-4598-9b65-ebd3628d46e4 ↗2026/10/30 09:17:33

许可证：apache-2.0。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。