Back to leaderboard

qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx

LM-STUDIO MLX

qwen3_moe · 30B · MXFP4

Excellent

Apr 22, 2026 · Apple M2 Max

qwen3.8:27b

OLLAMA GGUF

qwen35 · 27.3B · Q4_K_M

Excellent

Oct 3, 2026 · Cortex-X925

Global Score
95 vs 84
Hardware Fit
94 vs 66
Quality Score
96 vs 92

Hardware

qwen3-30b-a3b-thin… qwen3.8:27b
MachineMac StudioNVIDIA NVIDIA_DGX_Spark
CPUApple M2 MaxCortex-X925
Cores1220
RAM96 GB122 GB
GPUApple M2 MaxDevice 2e12
OSmacOS 26.1Ubuntu 24.04.5 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

qwen3-30b-a3b-thin… qwen3.8:27b
Tokens/sec80.429.4
First chunk46 ms306 ms
TTFT1.8 s4.8 s
Load timeN/A5.3 s
Memory usage21.2 GB16.2 GB
Memory %22%13%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

Speed
50/50
TTFT
14/20
Memory
30/30

qwen3.8:27b

Speed
31/50
TTFT
5/20
Memory
30/30

Quality

qwen3-30b-a3b-thinking-…

Reasoning
19/20
Coding
18/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.8:27b

Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3-30b-a3b-thin… details | View qwen3.8:27b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest