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 20, 2026 · Apple M2 Max

qwen2.5-coder:7b

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Good

Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K

Global Score
97 vs 68
Hardware Fit
95 vs 59
Quality Score
98 vs 72

Hardware

qwen3-30b-a3b-thin… qwen2.5-coder:7b
MachineMac StudioASUS
CPUApple M2 MaxIntel Gen Intel® Core™ i7-13700K
Cores1224
RAM96 GB64 GB
GPUApple M2 MaxNVIDIA GeForce RTX 3070
OSmacOS 26.1Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown

Performance

qwen3-30b-a3b-thin… qwen2.5-coder:7b
Tokens/sec79.634.4
First chunk11 ms1991 ms
TTFT1.7 s2.0 s
Load time7.1 s40.6 s
Memory usage0.0 GB5.0 GB
Memory %0%8%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

Speed
50/50
TTFT
15/20
Memory
30/30

qwen2.5-coder:7b

Speed
38/50
TTFT
12/20
Memory
9/30

Quality

qwen3-30b-a3b-thinking-…

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

qwen2.5-coder:7b

Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3-30b-a3b-thin… details | View qwen2.5-coder:7b 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