Back to leaderboard

qwen/qwen3.6-35b-a3b

LM-STUDIO MLX

qwen3_5_moe · 35B · 6bit

Excellent

Jul 17, 2026 · Apple M5 Max

tinyllama

OLLAMA GGUF
Marginal

Mar 6, 2026 · Apple M4

Global Score
87 vs 43
Hardware Fit
90 vs 100
Quality Score
86 vs 19

Hardware

qwen/qwen3.6-35b-a3b tinyllama
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 tinyllama
Tokens/sec86.5133.4
First chunk9 ms61 ms
TTFT175 ms61 ms
Load timeN/A0.5 s
Memory usage37.9 GB0.2 GB
Memory %59%1%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b

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

tinyllama

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

Quality

qwen/qwen3.6-35b-a3b

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

tinyllama

Reasoning
2/20
Coding
2/20
Instruction
7/20
Structured
5/15
Math
0/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak
View qwen/qwen3.6-35b-a3b details | View tinyllama 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