Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Not Rec.

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

starling-lm:7b

OLLAMA GGUF

llama · 7B · Q4_0

Good

Mar 6, 2026 · Apple M4

Global Score
65 vs 65
Hardware Fit
73 vs 96
Quality Score
62 vs 52

Hardware

qwen3.5:4b starling-lm:7b
MachineAZW GTR ProMacBook Air
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM125 GB32 GB
GPUAMD Radeon 8060SApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen3.5:4b starling-lm:7b
Tokens/sec45.723.8
First chunk180 ms232 ms
TTFT30.0 s232 ms
Load time5.3 s0.4 s
Memory usage16.2 GB5.3 GB
Memory %13%17%

HW Fit Score Breakdown

qwen3.5:4b

Speed
43/50
TTFT
0/20
Memory
30/30

starling-lm:7b

Speed
46/50
TTFT
20/20
Memory
30/30

Quality

qwen3.5:4b

Reasoning
17/20
Coding
1/20
Instruction
13/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Strong Multilingual: Strong

starling-lm:7b

Reasoning
10/20
Coding
13/20
Instruction
8/20
Structured
3/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Adequate Multilingual: Strong
View qwen3.5:4b details | View starling-lm: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