Mixtral-8x7B-Instruct-v0.1-FP8-KV

amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV

3.2B parametersLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
1,274
Total downloads
116.8K
Gained 7D
+441(increase)
0.4%(up) vs baseline
Gained 30D
—
Likes
3
+0 in 7D
Rank · tracked models
#30,722
372(down 372 places)this week
Parameters
3.2B
Last source update
Jun 18, 2026
Momentum
43.5
  • Mixtral-8x7B-Instruct-v0.1-FP8-KV gained 441 downloads during the last seven tracked days.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Mixtral-8x7B-Instruct-v0.1-FP8-KV is an AI model published by amd. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 26h ago.

Published
Sep 10, 2024
Last updated
Jun 18, 2026
Library
—
License
apache-2.0
Task
—
Parameters
3,164,688,384
Spaces
1
Derivative models
—
Velocity 7D/day
63
safetensorsmixtralvllm_cibase_model:mistralai/Mixtral-8x7B-Instruct-v0.1base_model:quantized:mistralai/Mixtral-8x7B-Instruct-v0.1license:apache-2.0fp8region:us

Model family

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

Similar models

Models similar to Mixtral-8x7B-Instruct-v0.1-FP8-KV
ModelDL 30D
K2-Horizon-7B-AWQ-INT4cyankiwi373
Elixir-Qwen2.5-Coder-3Bjmarceno318
Qwen2.5-3B-Instruct-unsloth-bnb-4bitunsloth88.5K
Qwen2.5-3B-unsloth-bnb-4bitunsloth4,047
Qwen2.5-3B-bnb-4bitunsloth2,765
Qwen2.5-3B-Instruct-bnb-4bitunsloth38.1K
amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV — Downloads, Growth & Stats | OpenModelStats