Back to leaderboard

mistral:latest

OLLAMA GGUF

llama · 7.2B · Q4_K_M

Good

May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor

qwen3-vl:4b-instruct

OLLAMA GGUF

qwen3vl · 4.4B · Q4_K_M

Excellent

Apr 20, 2026 · Apple M2 Max

Global Score
73 vs 83
Hardware Fit
100 vs 96
Quality Score
62 vs 78

Hardware

mistral:latest qwen3-vl:4b-instruct
MachineMicro-Star International Co., Ltd. MS-7B79Mac Studio
CPUAMD Ryzen 5 2600X Six-Core ProcessorApple M2 Max
Cores1212
RAM16 GB96 GB
GPUNVIDIA GeForce GTX 1080Apple M2 Max
OSMicrosoft Windows 11 Famille 10.0.26200macOS 26.1
Archx64arm64
Power Modebalancedbalanced

Performance

mistral:latest qwen3-vl:4b-instruct
Tokens/sec31.791.2
First chunk102 ms150 ms
TTFT102 ms150 ms
Load time14.3 s5.3 s
Memory usage4.8 GB42.5 GB
Memory %30%44%

HW Fit Score Breakdown

mistral:latest

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

qwen3-vl:4b-instruct

Speed
50/50
TTFT
20/20
Memory
26/30

Quality

mistral:latest

Reasoning
8/20
Coding
13/20
Instruction
16/20
Structured
12/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

qwen3-vl:4b-instruct

Reasoning
14/20
Coding
16/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

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