Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Good

Mar 12, 2026 · Apple M4 Pro

internlm2:7b

OLLAMA GGUF

internlm2 · 7.7B · Q4_0

Good

Mar 6, 2026 · Apple M4

Global Score
77 vs 77
Hardware Fit
67 vs 95
Quality Score
81 vs 69

Hardware

qwen3.5-9b-mlx internlm2:7b
MachineMac miniMacBook Air
CPUApple M4 ProApple M4
Cores1410
RAM64 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 15.7.4macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-9b-mlx internlm2:7b
Tokens/sec20.322.7
First chunk4216 ms250 ms
TTFT4.2 s250 ms
Load timeN/A0.7 s
Memory usage5.6 GB10.6 GB
Memory %9%33%

HW Fit Score Breakdown

qwen3.5-9b-mlx

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

internlm2:7b

Speed
45/50
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

internlm2:7b

Reasoning
12/20
Coding
10/20
Instruction
13/20
Structured
14/15
Math
11/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5-9b-mlx details | View internlm2:7b 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