Back to leaderboard

qwen3-4b-qwen3.6-plus-reasoning-distilled

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

starcoder2:3b

OLLAMA GGUF

starcoder2 · 3B · Q4_0

Not Rec.

Jun 26, 2026 · Cortex-A78AE

Global Score
65 vs 35
Hardware Fit
96 vs 100
Quality Score
51 vs 7

Hardware

qwen3-4b-qwen3.6-p… starcoder2:3b
MachineMac StudioNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M2 MaxCortex-A78AE
Cores126
RAM96 GB7 GB
GPUApple M2 MaxIntegrated / Unknown
OSmacOS 26.1Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3-4b-qwen3.6-p… starcoder2:3b
Tokens/sec99.631.5
First chunk18 ms392 ms
TTFT1.6 s392 ms
Load time4.8 s4.8 s
Memory usage0.3 GB1.8 GB
Memory %0%24%

HW Fit Score Breakdown

qwen3-4b-qwen3.6-plus-r…

Speed
50/50
TTFT
16/20
Memory
30/30

starcoder2:3b

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

Quality

qwen3-4b-qwen3.6-plus-r…

Reasoning
8/20
Coding
4/20
Instruction
14/20
Structured
9/15
Math
8/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Adequate Multilingual: Strong

starcoder2:3b

Reasoning
0/20
Coding
3/20
Instruction
1/20
Structured
0/15
Math
1/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
View qwen3-4b-qwen3.6-p… details | View starcoder2:3b 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