Back to leaderboard

qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx

LM-STUDIO MLX

qwen3_moe · 30B · MXFP4

Excellent

Apr 20, 2026 · Apple M2 Max

llama-3.1-8b-instruct

LM-STUDIO GGUF

llama · 8B · Q8_0

Excellent

Apr 26, 2026 · AMD Ryzen 5 5500

Global Score
97 vs 81
Hardware Fit
95 vs 100
Quality Score
98 vs 73

Hardware

qwen3-30b-a3b-thin… llama-3.1-8b-instr…
MachineMac StudioASUS
CPUApple M2 MaxAMD Ryzen 5 5500
Cores1212
RAM96 GB31 GB
GPUApple M2 MaxNavi 44 [Radeon RX 9060 XT]
OSmacOS 26.1Nobara Linux 43
Archarm64x64
Power Modebalancedperformance

Performance

qwen3-30b-a3b-thin… llama-3.1-8b-instr…
Tokens/sec79.635.6
First chunk11 ms52 ms
TTFT1.7 s256 ms
Load time7.1 sN/A
Memory usage0.0 GB8.6 GB
Memory %0%28%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

Speed
50/50
TTFT
15/20
Memory
30/30

llama-3.1-8b-instruct

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

Quality

qwen3-30b-a3b-thinking-…

Reasoning
19/20
Coding
19/20
Instruction
20/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

llama-3.1-8b-instruct

Reasoning
13/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3-30b-a3b-thin… details | View llama-3.1-8b-instr… 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