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

qwen3.5:2b

OLLAMA GGUF

qwen35 · 2.3B · Q8_0

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

Global Score
97 vs 13
Hardware Fit
95 vs 41
Quality Score
98 vs 1

Hardware

qwen3-30b-a3b-thin… qwen3.5:2b
MachineMac StudioLENOVO 20L7CTO1WW
CPUApple M2 MaxIntel Core™ i5-8350U
Cores128
RAM96 GB23 GB
GPUApple M2 MaxKaby Lake-R GT2 [UHD Graphics 620]
OSmacOS 26.1Fedora Linux 43
Archarm64x64
Power Modebalancedlow-power

Performance

qwen3-30b-a3b-thin… qwen3.5:2b
Tokens/sec79.64.5
First chunk11 ms1413 ms
TTFT1.7 s31.1 s
Load time7.1 s7.1 s
Memory usage0.0 GB3.8 GB
Memory %0%16%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

qwen3.5:2b

Speed
11/50
TTFT
0/20
Memory
30/30

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

qwen3.5:2b

Reasoning
0/20
Coding
0/20
Instruction
1/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
View qwen3-30b-a3b-thin… details | View qwen3.5:2b 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