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

richardyoung/qwythos-9b-abliterated:Q8_0

OLLAMA GGUF

qwen35 · 9.0B · Q8_0

Good

Jun 28, 2026 · Apple M4 Pro

Global Score
97 vs 65
Hardware Fit
95 vs 96
Quality Score
98 vs 52

Hardware

qwen3-30b-a3b-thin… richardyoung/qwyth…
MachineMac StudioMac mini
CPUApple M2 MaxApple M4 Pro
Cores1212
RAM96 GB24 GB
GPUApple M2 MaxApple M4 Pro
OSmacOS 26.1macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… richardyoung/qwyth…
Tokens/sec79.625.3
First chunk11 ms397 ms
TTFT1.7 s397 ms
Load time7.1 s6.3 s
Memory usage0.0 GB8.3 GB
Memory %0%34%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

richardyoung/qwythos-9b…

Speed
47/50
TTFT
20/20
Memory
29/30

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

richardyoung/qwythos-9b…

Reasoning
18/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
1/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor

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