Back to leaderboard

qwen/qwen3-8b

LM-STUDIO MLX

qwen3 · 8B · 4bit

Excellent

Mar 5, 2026 · Apple M4 Pro

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

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
89 vs 88
Hardware Fit
95 vs 94
Quality Score
87 vs 85

Hardware

qwen/qwen3-8b huihui-qwen3.6-35b…
MachineMac miniGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUApple M4 ProAMD Ryzen 5 5600X 6-Core Processor
Cores1412
RAM64 GB47 GB
GPUApple M4 ProAD106 [GeForce RTX 4060 Ti]
OSmacOS 15.7.4cachyos rolling
Archarm64x64
Power Modebalancedlow-power

Performance

qwen/qwen3-8b huihui-qwen3.6-35b…
Tokens/sec33.439.8
First chunk257 ms3 ms
TTFT257 ms479 ms
Load timeN/AN/A
Memory usage4.3 GB24.4 GB
Memory %7%52%

HW Fit Score Breakdown

qwen/qwen3-8b

Speed
45/50
TTFT
20/20
Memory
30/30

huihui-qwen3.6-35b-a3b-…

Speed
50/50
TTFT
20/20
Memory
24/30

Quality

qwen/qwen3-8b

Reasoning
19/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

huihui-qwen3.6-35b-a3b-…

Reasoning
18/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen/qwen3-8b 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