Skip to main content
Back to Explore

DeepSeek R1 0528 Qwen3 8B

DeepSeek·Released 2025-05-29
Open Source8BMITMoE
CompareView model repository

Related Models

DeepSeek: DeepSeek V4 Pro2026-04-24DeepSeek V4 Pro (Reasoning, High Effort)2026-04-24DeepSeek: DeepSeek V4 Flash2026-04-24DeepSeek V4 Flash (Reasoning, High Effort)2026-04-24DeepSeek V4 Pro (Non-reasoning)2026-04-24DeepSeek V4 Flash (Non-reasoning)2026-04-24DeepSeek: DeepSeek V4 Flash (free)2026-04-24DeepSeek V3.2 (Reasoning)2025-12-01

Benchmarks

MMLU-Pro
73.9%
GPQA Diamond
61.2%
HLE
5.6%
LiveCodeBench
51.3%
SciCode
20.4%
TerminalBench Hard
1.5%
MATH-500
93.2%
AIME
65.0%
AIME 2025
63.7%
IFBench
19.9%
Long Context Recall
13.0%
Tau2
0.0%
Market AverageTop Score

Open Source

View model repository
mit8BGGUF / GPTQ / AWQ
Downloads

895.5K

Likes

1.1K

VRAM (FP16)

8-16 GB

GPU

RTX 4070 / M2 Pro

Quick Compare

Similar Models

DeepSeek V3 (Dec '24)

DeepSeek

Q: 10.4$0.52/1M
Coding: +8.6

Nova 2.0 Omni (Non-reasoning)

Amazon

Q: 10.5$0.85/1M
Coding: +6.0

Qwen3 32B (Reasoning)

Alibaba

Q: 10.5$0.28/1M
Coding: +6.0

EXAONE 4.0 32B (Reasoning)

LG AI Research

Q: 10.6N/A/1M
Coding: +6.2

Qwen3 VL 8B (Reasoning)

Alibaba

Q: 10.6$0.66/1M

Qwen3.5 2B

Alibaba

Q: 10.2$0.04/1M
Coding: +11.9
Compare all 7 models