AI NEWS.ccAI正在发生 未来正在更新
♡ 我的收藏 0
AI 模型库/dbirks/Qwen3.8-27B-W4A16-AutoRound
MODEL PROFILE · 模型档案

Qwen3.8-27B-W4A16-AutoRound

dbirks · Qwen3.8-27B-W4A16-AutoRound

An int4 weight-only (W4A16) quantization of Qwen/Qwen3.8-27B, made with Intel AutoRound and packaged in compressed-tensors for vLLM. The weights are int4 and the activations stay BF16, so it runs on any Ampere-or-newer NVIDIA GPU through the Marlin int4 kernel — no Blackwell needed. It's about 19.5 GB on disk, down from roughly 52 GB at BF16. This build is aimed at non-Blackwell GPUs. If you have a Blackwell card (RTX 50-series, B200, DGX Spark), the NVFP4 (W4A4) sibling uses the FP4 tensor cores and will be faster. Accuracy notes are in the Evaluation section below. - **Base model:** `Qwen/Qwen3.8-27B` — a hybrid **GatedDeltaNet (linear-attention) + full-attention** multimodal decoder (64 layers: 48 linear-attn + 16 full-attn) with a vision tower; 262K context. - **Quantization:** int4 **W4A16** (weight-only, group size 128) on the language-decoder `Linear` layers, **except** the two tiny per-layer recurrence-control projections (`in_proj_a`, `in_proj_b`) which stay BF16. - **Kept BF16:** `linear_attn.in_proj_a` / `in_proj_b`, the entire `visual.*` vision tower, the `mtp` head, and `lm_head`. - **Format:** compressed-tensors (`pack-quantized`), auto-detected by vLLM (Marlin int4). - **Quantizer:** Intel AutoRound (arXiv:2309.05516), SignRound block reconstruction.

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2026/10/31 12:34:20
OVERVIEW

模型介绍

An int4 weight-only (W4A16) quantization of Qwen/Qwen3.8-27B, made with Intel AutoRound and packaged in compressed-tensors for vLLM. The weights are int4 and the activations stay BF16, so it runs on any Ampere-or-newer NVIDIA GPU through the Marlin int4 kernel — no Blackwell needed. It's about 19.5 GB on disk, down from roughly 52 GB at BF16. This build is aimed at non-Blackwell GPUs. If you have a Blackwell card (RTX 50-series, B200, DGX Spark), the NVFP4 (W4A4) sibling uses the FP4 tensor cores and will be faster. Accuracy notes are in the Evaluation section below. - **Base model:** `Qwen/Qwen3.8-27B` — a hybrid **GatedDeltaNet (linear-attention) + full-attention** multimodal decoder (64 layers: 48 linear-attn + 16 full-attn) with a vision tower; 262K context. - **Quantization:** int4 **W4A16** (weight-only, group size 128) on the language-decoder `Linear` layers, **except** the two tiny per-layer recurrence-control projections (`in_proj_a`, `in_proj_b`) which stay BF16. - **Kept BF16:** `linear_attn.in_proj_a` / `in_proj_b`, the entire `visual.*` vision tower, the `mtp` head, and `lm_head`. - **Format:** compressed-tensors (`pack-quantized`), auto-detected by vLLM (Marlin int4). - **Quantizer:** Intel AutoRound (arXiv:2309.05516), SignRound block reconstruction.

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 · dbirks/Qwen3.8-27B-W4A16-AutoRound ↗2026/10/31 12:34:20
huggingface · enrich:425ceae7-5d24-49b0-a2d2-52a7e35f80f6 ↗2026/10/29 16:58:58

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。