Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

granite4.2:3b

OLLAMA GGUF

granite · 3.7B · Q4_K_M

Excellent

Aug 29, 2026 · Apple M1 Pro

Global Score
57 vs 80
Hardware Fit
61 vs 80
Quality Score
55 vs 80

Hardware

qwen3.5:9b granite4.2:3b
MachineAZW GTR ProMacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M1 Pro
Cores3210
RAM125 GB16 GB
GPUAMD Radeon 8060SApple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen3.5:9b granite4.2:3b
Tokens/sec30.346.8
First chunk205 ms135 ms
TTFT8.7 s135 ms
Load time5.6 s0.0 s
Memory usage18.8 GB12.7 GB
Memory %15%79%

HW Fit Score Breakdown

qwen3.5:9b

Speed
30/50
TTFT
1/20
Memory
30/30

granite4.2:3b

Speed
50/50
TTFT
20/20
Memory
10/30

Quality

qwen3.5:9b

Reasoning
17/20
Coding
2/20
Instruction
7/20
Structured
8/15
Math
12/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong

granite4.2:3b

Reasoning
18/20
Coding
13/20
Instruction
12/20
Structured
15/15
Math
14/15
Multilingual
8/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:9b details | View granite4.2:3b 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