Back to leaderboard

qwen/qwen3.6-35b-a3b:2

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Good

Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor

microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score
73 vs 62
Hardware Fit
50 vs 99
Quality Score
83 vs 46

Hardware

qwen/qwen3.6-35b-a… microsoft/phi-4-mi…
MachineSystem manufacturerMacBook Air
CPUAMD Ryzen 7 5800X 8-Core ProcessorApple M4
Cores1610
RAM31 GB32 GB
GPUNavi 44 [Radeon RX 9060 XT]Apple M4
OSUbuntu 26.04.1 LTSmacOS 26.3
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen/qwen3.6-35b-a… microsoft/phi-4-mi…
Tokens/sec10.540.3
First chunk4 ms289 ms
TTFT1.7 s289 ms
Load timeN/AN/A
Memory usage21.4 GB2.0 GB
Memory %69%6%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b:2

Speed
16/50
TTFT
18/20
Memory
16/30

microsoft/phi-4-mini-re…

Speed
50/50
TTFT
20/20
Memory
29/30

Quality

qwen/qwen3.6-35b-a3b:2

Reasoning
16/20
Coding
15/20
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

microsoft/phi-4-mini-re…

Reasoning
7/20
Coding
6/20
Instruction
7/20
Structured
7/15
Math
12/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Adequate

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