Back to leaderboard

qwen2.5:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

Jun 17, 2026 · ZHAOXIN KaiXian KX-7000 KaiXian KX-7000

qwen3.6-35b-a3b-claude-4.7-opus-reasoning-distilled-apex

LM-STUDIO GGUF

qwen35moe · 35B

Excellent

Jul 17, 2026 · Apple M5 Max

Global Score
65 vs 90
Hardware Fit
87 vs 98
Quality Score
56 vs 86

Hardware

qwen2.5:1.5b qwen3.6-35b-a3b-cl…
MachineShanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRBMacBook Pro
CPUZHAOXIN KaiXian KX-7000 KaiXian KX-7000Apple M5 Max
Cores818
RAM30 GB64 GB
GPUZX C-1190Apple M5 Max
OSMicrosoft Windows 11 Pro 10.0.26100macOS 27.0
Archx64arm64
Power Modebalancedbalanced

Performance

qwen2.5:1.5b qwen3.6-35b-a3b-cl…
Tokens/sec16.886.6
First chunk941 ms13 ms
TTFT941 ms143 ms
Load time0.2 sN/A
Memory usage1.0 GB23.9 GB
Memory %3%37%

HW Fit Score Breakdown

qwen2.5:1.5b

Speed
37/50
TTFT
20/20
Memory
30/30

qwen3.6-35b-a3b-claude-…

Speed
50/50
TTFT
20/20
Memory
28/30

Quality

qwen2.5:1.5b

Reasoning
8/20
Coding
10/20
Instruction
12/20
Structured
13/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

qwen3.6-35b-a3b-claude-…

Reasoning
18/20
Coding
17/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen2.5:1.5b details | View qwen3.6-35b-a3b-cl… 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