AI NEWS.ccAI正在发生 未来正在更新
♡ 我的收藏 0
AI 模型库/amd/Qwen3.8-27B-Quark-AWQ-INT4-W4A16
MODEL PROFILE · 模型档案

Qwen3.8-27B-Quark-AWQ-INT4-W4A16

amd · Qwen3.8-27B-Quark-AWQ-INT4-W4A16

INT4 weight-only (W4A16) quantized version of `Qwen/Qwen3.8-27B`, produced with the **AWQ** algorithm using AMD Quark. \* BFCL Overall Acc reflects only `single_turn` categories, not the full Gorilla-leaderboard formula (multi-turn/web-search/memory categories were not run and would count as 0 against the public leaderboard's own Overall Acc). Sub-metrics: Non-Live AST 86.58% (base 88.52%), Live AST 81.57% (base 83.05%), Relevance Detection 75.00% (base 75.00%), Irrelevance Detection 72.47% (base 72.22%). Recovery % = quantized / BF16-base, using flexible-extract for GSM8K rows and base/quantized (inverted, since lower is better) for perplexity — both measured by us against verified-upstream `Qwen/Qwen3.8-27B` weights, not vendor-reported numbers. GSM8K uses `lm-evaluation-harness`; non-thinking mode is approximated by pre-closing an empty ` ` block in the prompt, since the harness task is a raw few-shot completion rather than a chat-templated request. BFCL run via the official `bfcl_eval` harness.

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 19:17:06
OVERVIEW

模型介绍

INT4 weight-only (W4A16) quantized version of `Qwen/Qwen3.8-27B`, produced with the **AWQ** algorithm using AMD Quark. \* BFCL Overall Acc reflects only `single_turn` categories, not the full Gorilla-leaderboard formula (multi-turn/web-search/memory categories were not run and would count as 0 against the public leaderboard's own Overall Acc). Sub-metrics: Non-Live AST 86.58% (base 88.52%), Live AST 81.57% (base 83.05%), Relevance Detection 75.00% (base 75.00%), Irrelevance Detection 72.47% (base 72.22%). Recovery % = quantized / BF16-base, using flexible-extract for GSM8K rows and base/quantized (inverted, since lower is better) for perplexity — both measured by us against verified-upstream `Qwen/Qwen3.8-27B` weights, not vendor-reported numbers. GSM8K uses `lm-evaluation-harness`; non-thinking mode is approximated by pre-closing an empty ` ` block in the prompt, since the harness task is a raw few-shot completion rather than a chat-templated request. BFCL run via the official `bfcl_eval` harness.

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 · amd/Qwen3.8-27B-Quark-AWQ-INT4-W4A16 ↗2026/10/30 03:09:36
huggingface · enrich:1892f927-1c7b-4b77-a377-6f185070325b ↗2026/10/30 12:44:16

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。