Qwen3.8-27B-MTP-W4A16-VOLTA-Ampere

Israeli-AI/Qwen3.8-27B-MTP-W4A16-VOLTA-Ampere

Text Generation27.8B parametersLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
1,079
Total downloads
2,673
Gained 7D
+75(increase)
2.9%(up) vs baseline
Gained 30D
—
Likes
2
+0 in 7D
Rank · tracked models
#29,937
6367(down 6367 places)this week
Parameters
27.8B
Last source update
Sep 1, 2026
Momentum
36.0
  • Qwen3.8-27B-MTP-W4A16-VOLTA-Ampere gained 75 downloads during the last seven tracked days.
  • It moved from #6203 to #7948 among tracked Text Generation models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Qwen3.8-27B-MTP-W4A16-VOLTA-Ampere is a text generation model published by Israeli-AI. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Sep 20, 2026.

Published
Aug 15, 2026
Last updated
Sep 1, 2026
Library
—
License
apache-2.0
Task
Text Generation
Parameters
27,781,427,952
Spaces
0
Derivative models
—
Velocity 7D/day
11
safetensorsqwen3_5w4a16compressed-tensorsint4voltav100sm70mtpspeculative-decodingvllmcmp-170hx

Model family

Based on base-model relationships reported by the source's metadata.

Similar models

Models similar to Qwen3.8-27B-MTP-W4A16-VOLTA-Ampere
ModelDL 30D
Qwen3.8-27B-OBLITERATEDOBLITERATUS1.2M
Qwen3.8-27B-GPTQ-Int4-sym-G128-MTP-BF16SergiioB45.4K
EVE-27b-XENO-HAT-DeepSeek-V4-Flashwin1034.2K
Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16AEON-710.8K
Qwen3.8-27B-GPTQ-Int4-V100Max7333310.8K
gemma3.8-27B-FP8ark400410.5K
Israeli-AI/Qwen3.8-27B-MTP-W4A16-VOLTA-Ampere — Downloads, Growth & Stats | OpenModelStats