Back to leaderboard

qwen/qwen3.6-35b-a3b

LM-STUDIO MLX

qwen3_5_moe · 35B · 4bit

Excellent

Oct 20, 2026 · Apple M1 Pro

phi4:14b

OLLAMA GGUF

phi3 · 14.7B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

Global Score
84 vs 77
Hardware Fit
78 vs 74
Quality Score
86 vs 78

Hardware

qwen/qwen3.6-35b-a3b phi4:14b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M1 ProCortex-X925
Cores1020
RAM32 GB122 GB
GPUApple M1 ProDevice 2e12
OSmacOS 15.6.1Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

qwen/qwen3.6-35b-a3b phi4:14b
Tokens/sec49.922.9
First chunk31 ms198 ms
TTFT708 ms198 ms
Load timeN/A10.3 s
Memory usage26.6 GB14.7 GB
Memory %83%12%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b

Speed
50/50
TTFT
20/20
Memory
8/30

phi4:14b

Speed
24/50
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

phi4:14b

Reasoning
18/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen/qwen3.6-35b-a3b details | View phi4:14b 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