Back to leaderboard

devstral:latest

OLLAMA GGUF

llama · 23.6B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

qwen3-vl-4b-instruct

LM-STUDIO GGUF

qwen3vl · 4B · Q4_K_M

Excellent

Apr 20, 2026 · Apple M2 Max

Global Score
80 vs 87
Hardware Fit
79 vs 100
Quality Score
80 vs 81

Hardware

devstral:latest qwen3-vl-4b-instruct
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4Mac Studio
CPUIntel Core™ i5-14400FApple M2 Max
Cores1612
RAM32 GB96 GB
GPUNVIDIA GeForce RTX 5060 TiApple M2 Max
OSMicrosoft Windows 11 Professionnel 10.0.26200macOS 26.1
Archx64arm64
Power Modebalancedbalanced

Performance

devstral:latest qwen3-vl-4b-instruct
Tokens/sec20.071.6
First chunk146 ms5 ms
TTFT146 ms157 ms
Load time6.5 sN/A
Memory usage14.2 GB20.5 GB
Memory %45%21%

HW Fit Score Breakdown

devstral:latest

Speed
33/50
TTFT
20/20
Memory
26/30

qwen3-vl-4b-instruct

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

Quality

devstral:latest

Reasoning
16/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
9/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

qwen3-vl-4b-instruct

Reasoning
15/20
Coding
17/20
Instruction
17/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Strong 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