Back to leaderboard

devstral:latest

OLLAMA GGUF

llama · 23.6B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Good

Mar 12, 2026 · Apple M4 Pro

Global Score
80 vs 77
Hardware Fit
79 vs 67
Quality Score
80 vs 81

Hardware

devstral:latest qwen3.5-9b-mlx
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4Mac mini
CPUIntel Core™ i5-14400FApple M4 Pro
Cores1614
RAM32 GB64 GB
GPUNVIDIA GeForce RTX 5060 TiApple M4 Pro
OSMicrosoft Windows 11 Professionnel 10.0.26200macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced

Performance

devstral:latest qwen3.5-9b-mlx
Tokens/sec20.020.3
First chunk146 ms4216 ms
TTFT146 ms4.2 s
Load time6.5 sN/A
Memory usage14.2 GB5.6 GB
Memory %45%9%

HW Fit Score Breakdown

devstral:latest

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

qwen3.5-9b-mlx

Speed
29/50
TTFT
8/20
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

qwen3.5-9b-mlx

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
10/10
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