Back to leaderboard

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

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

yi-coder-1.5b-chat

LM-STUDIO GGUF

llama · 1.5B · Q4_K_M

Marginal

Mar 7, 2026 · Intel Core™ i5-5300U

Global Score
65 vs 45
Hardware Fit
96 vs 67
Quality Score
51 vs 35

Hardware

qwen3-4b-qwen3.6-p… yi-coder-1.5b-chat
MachineMac StudioLENOVO 20BUS00700
CPUApple M2 MaxIntel Core™ i5-5300U
Cores124
RAM96 GB16 GB
GPUApple M2 MaxIntel(R) HD Graphics 5500
OSmacOS 26.1Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-4b-qwen3.6-p… yi-coder-1.5b-chat
Tokens/sec99.67.7
First chunk18 ms2668 ms
TTFT1.6 s2.7 s
Load time4.8 sN/A
Memory usage0.3 GB0.9 GB
Memory %0%6%

HW Fit Score Breakdown

qwen3-4b-qwen3.6-plus-r…

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

yi-coder-1.5b-chat

Speed
26/50
TTFT
17/20
Memory
24/30

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

yi-coder-1.5b-chat

Reasoning
4/20
Coding
12/20
Instruction
6/20
Structured
6/15
Math
1/15
Multilingual
6/10
Reasoning: Poor Coding: Adequate Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Adequate
View qwen3-4b-qwen3.6-p… details | View yi-coder-1.5b-chat 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