Back to leaderboard

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

LM-STUDIO MLX

qwen3_moe · 30B · MXFP4

Excellent

Aug 20, 2026 · Apple M4 Max

qwen3.5-35b-a3b-t48-c8k:latest

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Aug 1, 2026 · Intel Xeon® E5-4620 0

Global Score
96 vs 65
Hardware Fit
95 vs 38
Quality Score
96 vs 76

Hardware

qwen3-30b-a3b-thin… qwen3.5-35b-a3b-t4…
MachineMacBook ProDell Inc. PowerEdge R820
CPUApple M4 MaxIntel Xeon® E5-4620 0
Cores1664
RAM128 GB256 GB
GPUApple M4 MaxMicrosoft Remote Display Adapter, Microsoft Basic Display Adapter
OSmacOS 26.5.2Microsoft Windows Server 2022 Datacenter 10.0.20348
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… qwen3.5-35b-a3b-t4…
Tokens/sec112.83.4
First chunk21 ms4210 ms
TTFT1.5 s4.2 s
Load time3.5 s45.1 s
Memory usage0.0 GB22.0 GB
Memory %0%9%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

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

qwen3.5-35b-a3b-t48-c8k…

Speed
3/50
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

qwen3.5-35b-a3b-t48-c8k…

Reasoning
16/20
Coding
15/20
Instruction
9/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3-30b-a3b-thin… details | View qwen3.5-35b-a3b-t4… 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