Back to leaderboard

minimax-m2.7:cloud

OLLAMA GGUF

minimax

Not Rec.

Apr 1, 2026 · Apple M4

qwen/qwen3-vl-30b

LM-STUDIO GGUF

qwen3vlmoe · 30B · Q4_K_M

Excellent

Apr 24, 2026 · AMD Ryzen 5 5500

Global Score
74 vs 92
Hardware Fit
34 vs 95
Quality Score
91 vs 90

Hardware

minimax-m2.7:cloud qwen/qwen3-vl-30b
MachineMac miniASUS
CPUApple M4AMD Ryzen 5 5500
Cores1012
RAM24 GB31 GB
GPUApple M4Navi 44 [Radeon RX 9060 XT]
OSmacOS 26.3Nobara Linux 43
Archarm64x64
Power Modebalancedperformance

Performance

minimax-m2.7:cloud qwen/qwen3-vl-30b
Tokens/sec0.024.8
First chunk7588 ms11 ms
TTFT11.4 s735 ms
Load time0.0 s11.7 s
Memory usage0.7 GB0.6 GB
Memory %3%2%

HW Fit Score Breakdown

minimax-m2.7:cloud

Speed
0/50
TTFT
4/20
Memory
30/30

qwen/qwen3-vl-30b

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

Quality

minimax-m2.7:cloud

Reasoning
19/20
Coding
18/20
Instruction
15/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen/qwen3-vl-30b

Reasoning
19/20
Coding
19/20
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
View minimax-m2.7:cloud details | View qwen/qwen3-vl-30b 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