Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Good

Mar 12, 2026 · Apple M4 Pro

mistral-small:24b

OLLAMA GGUF

llama · 23.6B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

Global Score
77 vs 75
Hardware Fit
67 vs 64
Quality Score
81 vs 80

Hardware

qwen3.5-9b-mlx mistral-small:24b
MachineMac miniNVIDIA NVIDIA_DGX_Spark
CPUApple M4 ProCortex-X925
Cores1420
RAM64 GB122 GB
GPUApple M4 ProDevice 2e12
OSmacOS 15.7.4Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

qwen3.5-9b-mlx mistral-small:24b
Tokens/sec20.314.3
First chunk4216 ms327 ms
TTFT4.2 s327 ms
Load timeN/A12.0 s
Memory usage5.6 GB18.5 GB
Memory %9%15%

HW Fit Score Breakdown

qwen3.5-9b-mlx

Speed
29/50
TTFT
8/20
Memory
30/30

mistral-small:24b

Speed
14/50
TTFT
20/20
Memory
30/30

Quality

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

mistral-small:24b

Reasoning
16/20
Coding
18/20
Instruction
14/20
Structured
13/15
Math
9/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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