Back to leaderboard

qwen2.5-7b-instruct

LM-STUDIO MLX

qwen2 · 7B · 4bit

Excellent

Mar 3, 2026 · Apple M4

huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 13, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
84 vs 88
Hardware Fit
97 vs 85
Quality Score
78 vs 89

Hardware

qwen2.5-7b-instruct huihui-qwen3.6-35b…
MachineMacBook AirGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUApple M4AMD Ryzen 5 5600X 6-Core Processor
Cores1012
RAM32 GB47 GB
GPUApple M4AD106 [GeForce RTX 4060 Ti]
OSmacOS 26.3cachyos rolling
Archarm64x64
Power Modebalancedlow-power

Performance

qwen2.5-7b-instruct huihui-qwen3.6-35b…
Tokens/sec24.437.7
First chunk464 ms18 ms
TTFT464 ms2.9 s
Load timeN/AN/A
Memory usage4.0 GB26.1 GB
Memory %13%56%

HW Fit Score Breakdown

qwen2.5-7b-instruct

Speed
47/50
TTFT
20/20
Memory
30/30

huihui-qwen3.6-35b-a3b-…

Speed
50/50
TTFT
13/20
Memory
22/30

Quality

qwen2.5-7b-instruct

Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

huihui-qwen3.6-35b-a3b-…

Reasoning
19/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen2.5-7b-instruct details | View huihui-qwen3.6-35b… 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