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

hermes3:8b

OLLAMA GGUF

llama · 8.0B · Q4_0

Good

Mar 6, 2026 · Apple M4

Global Score
97 vs 74
Hardware Fit
95 vs 94
Quality Score
98 vs 65

Hardware

qwen3-30b-a3b-thin… hermes3:8b
MachineMac StudioMacBook Air
CPUApple M2 MaxApple M4
Cores1210
RAM96 GB32 GB
GPUApple M2 MaxApple M4
OSmacOS 26.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… hermes3:8b
Tokens/sec79.622.3
First chunk11 ms296 ms
TTFT1.7 s296 ms
Load time7.1 s0.8 s
Memory usage0.0 GB10.2 GB
Memory %0%32%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

hermes3:8b

Speed
44/50
TTFT
20/20
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

hermes3:8b

Reasoning
11/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3-30b-a3b-thin… details | View hermes3:8b 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