AI NEWS.ccAI正在发生 未来正在更新
♡ 我的收藏 0
AI 模型库/keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF
MODEL PROFILE · 模型档案

Qwen3.6-VL-REAP-26B-A3B-GGUF

keithnull · Qwen3.6-VL-REAP-26B-A3B-GGUF

GGUF quantizations of atbender/Qwen3.6-VL-REAP-26B-A3B, a REAP-pruned variant of Qwen3.6-VL. **Both the language model (text quants) and the vision tower (mmproj) are included** - drop the mmproj alongside any text quant for full multimodal (image + text) inference. Each text quant was scored against the bf16 reference using `llama-perplexity` on the wikitext-2-raw test split (580 chunks, n_ctx=512, ~297k tokens). Bench run on a single RTX PRO 6000 (Blackwell, 96 GB). On Apple Silicon (llama.cpp, q8_0 KV cache): **Q4_K_M** had the best speed/quality trade-off across both standalone code-gen and agentic tasks. Q3_K_S held up reasonably well on quality at a smaller footprint, and IQ4_XS produced correct outputs but ran noticeably slower in the same harness. Your mileage may vary depending on your hardware and setup.

译文排队中，当前展示来源原文。

视觉问答multimodallicense: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 19:16:14
OVERVIEW

模型介绍

GGUF quantizations of atbender/Qwen3.6-VL-REAP-26B-A3B, a REAP-pruned variant of Qwen3.6-VL. **Both the language model (text quants) and the vision tower (mmproj) are included** - drop the mmproj alongside any text quant for full multimodal (image + text) inference. Each text quant was scored against the bf16 reference using `llama-perplexity` on the wikitext-2-raw test split (580 chunks, n_ctx=512, ~297k tokens). Bench run on a single RTX PRO 6000 (Blackwell, 96 GB). On Apple Silicon (llama.cpp, q8_0 KV cache): **Q4_K_M** had the best speed/quality trade-off across both standalone code-gen and agentic tasks. Q3_K_S held up reasonably well on quality at a smaller footprint, and IQ4_XS produced correct outputs but ran noticeably slower in the same harness. Your mileage may vary depending on your hardware and setup.

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 · keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF ↗2026/10/29 21:12:34
huggingface · enrich:980085af-41df-4e83-9efd-72751affceef ↗2026/10/30 09:24:37

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。