Back to leaderboard

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

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

gemma-3-4b-it-q4-k-m

OLLAMA GGUF

llama · 4B · Q4_K_M

Excellent

Jul 9, 2026 · Intel Core™ i5-10400

Global Score
65 vs 80
Hardware Fit
96 vs 100
Quality Score
51 vs 71

Hardware

qwen3-4b-qwen3.6-p… gemma-3-4b-it-q4-k-m
MachineMac StudioMac Pro
CPUApple M2 MaxIntel Core™ i5-10400
Cores1212
RAM96 GB32 GB
GPUApple M2 MaxAMD Radeon RX 6700 XT
OSmacOS 26.1macOS 26.5.1
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-4b-qwen3.6-p… gemma-3-4b-it-q4-k-m
Tokens/sec99.675.0
First chunk18 ms136 ms
TTFT1.6 s136 ms
Load time4.8 s0.0 s
Memory usage0.3 GB0.8 GB
Memory %0%3%

HW Fit Score Breakdown

qwen3-4b-qwen3.6-plus-r…

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

gemma-3-4b-it-q4-k-m

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

gemma-3-4b-it-q4-k-m

Reasoning
11/20
Coding
17/20
Instruction
14/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3-4b-qwen3.6-p… details | View gemma-3-4b-it-q4-k-m 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