Devstral-Small-2505.w4a16-gptq

mratsim/Devstral-Small-2505.w4a16-gptq

Text Generation23.9B parametersLicense: apache-2.0
Tracked by OpenModelStats since September 8, 2026View on Hugging Face ↗
Downloads 30D
129
Total downloads
19.3K
Gained 7D
+66(increase)
0.3%(up) vs baseline
Gained 30D
—
Likes
2
+0 in 7D
Rank · tracked models
#33,180
361(down 361 places)this week
Parameters
23.9B
Last source update
Sep 14, 2025
Momentum
25.4
  • Devstral-Small-2505.w4a16-gptq gained 66 downloads during the last seven tracked days.
  • It moved from #9422 to #9576 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

Devstral-Small-2505.w4a16-gptq is a text generation model published by mratsim. OpenModelStats has tracked the model since Sep 8, 2026, most recently observing it 24h ago.

Published
May 25, 2025
Last updated
Sep 14, 2025
Library
—
License
apache-2.0
Task
Text Generation
Parameters
23,919,744,560
Spaces
0
Derivative models
—
Velocity 7D/day
9
safetensorsmistralgptqvllmllmcompressortext-generation-inferencetext-generationdataset:nvidia/OpenCodeInstructbase_model:mistralai/Devstral-Small-2505base_model:quantized:mistralai/Devstral-Small-2505license:apache-2.0compressed-tensors

Model family

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

Base model

Sibling models

Similar models

Models similar to Devstral-Small-2505.w4a16-gptq
ModelDL 30D
GLM-4.5-Air-AWQ-FP16MixQuantTrio2,158
LFM2-24B-A2BLiquidAI3,327
LFM2-24B-A2B-MLX-4bitlmstudio-community82.4K
LFM2-24B-A2B-MLX-5bitlmstudio-community81.4K
LFM2-24B-A2B-MLX-8bitlmstudio-community81.3K
LFM2-24B-A2B-MLX-6bitlmstudio-community81.2K
mratsim/Devstral-Small-2505.w4a16-gptq — Downloads, Growth & Stats | OpenModelStats