Back to leaderboard

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

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

llama3.2:1b

OLLAMA GGUF

llama · 1.2B · Q8_0

Good

Jun 26, 2026 · Cortex-A78AE

Global Score
65 vs 63
Hardware Fit
96 vs 100
Quality Score
51 vs 47

Hardware

qwen3-4b-qwen3.6-p… llama3.2:1b
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… llama3.2:1b
Tokens/sec99.640.2
First chunk18 ms1087 ms
TTFT1.6 s1.1 s
Load time4.8 s6.2 s
Memory usage0.3 GB1.4 GB
Memory %0%19%

HW Fit Score Breakdown

qwen3-4b-qwen3.6-plus-r…

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

llama3.2:1b

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

llama3.2:1b

Reasoning
4/20
Coding
9/20
Instruction
14/20
Structured
13/15
Math
1/15
Multilingual
6/10
Reasoning: Poor Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
View qwen3-4b-qwen3.6-p… details | View llama3.2:1b 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