Back to leaderboard

qwen/qwen3.6-35b-a3b

LM-STUDIO MLX

qwen3_5_moe · 35B · 4bit

Excellent

Jul 17, 2026 · Apple M5 Max

phi-3-mini-128k-instruct

LM-STUDIO MLX

phi3 · 4bit

Not Rec.

Mar 4, 2026 · Apple M4

Global Score
89 vs 38
Hardware Fit
97 vs 100
Quality Score
86 vs 12

Hardware

qwen/qwen3.6-35b-a3b phi-3-mini-128k-in…
MachineMacBook ProMacBook Air
CPUApple M5 MaxApple M4
Cores1810
RAM64 GB32 GB
GPUApple M5 MaxApple M4
OSmacOS 27.0macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen/qwen3.6-35b-a3b phi-3-mini-128k-in…
Tokens/sec130.244.0
First chunk5 ms384 ms
TTFT135 ms385 ms
Load timeN/AN/A
Memory usage26.6 GB2.0 GB
Memory %42%6%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b

Speed
50/50
TTFT
20/20
Memory
27/30

phi-3-mini-128k-instruct

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

Quality

qwen/qwen3.6-35b-a3b

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

phi-3-mini-128k-instruct

Reasoning
3/20
Coding
2/20
Instruction
2/20
Structured
1/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
View qwen/qwen3.6-35b-a3b details | View phi-3-mini-128k-in… 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