Back to leaderboard

qwen3.5-9b

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Excellent

Mar 3, 2026 · Apple M4

vicuna:7b

OLLAMA GGUF

llama · 7B · Q4_0

Marginal

Mar 1, 2026 · Apple M4

Global Score
81 vs 59
Hardware Fit
84 vs 97
Quality Score
79 vs 43

Hardware

qwen3.5-9b vicuna:7b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-9b vicuna:7b
Tokens/sec20.423.4
First chunk3034 msN/A
TTFT3.0 s242 ms
Load timeN/A0.4 s
Memory usage5.6 GB5.8 GB
Memory %17%18%

HW Fit Score Breakdown

qwen3.5-9b

Speed
41/50
TTFT
14/20
Memory
29/30

vicuna:7b

Speed
37/50
TTFT
30/20
Memory
30/30

Quality

qwen3.5-9b

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

vicuna:7b

Reasoning
8/20
Coding
4/20
Instruction
10/20
Structured
12/15
Math
2/15
Multilingual
7/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
View qwen3.5-9b details | View vicuna: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