Back to leaderboard

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Nov 4, 2026 · Intel Core™ i7-9700

yi-coder:9b

OLLAMA GGUF

llama · 8.8B · Q4_0

Good

Mar 6, 2026 · Apple M4

Global Score
29 vs 70
Hardware Fit
84 vs 89
Quality Score
6 vs 62

Hardware

qwen3:4b yi-coder:9b
MachineVMware, Inc. VMware Virtual PlatformMacBook Air
CPUIntel Core™ i7-9700Apple M4
Cores410
RAM16 GB32 GB
GPUIntegrated / UnknownApple M4
OSUbuntu 24.04.5 LTSmacOS 26.3
Archx64arm64
Power Modeunknownbalanced

Performance

qwen3:4b yi-coder:9b
Tokens/sec10.419.4
First chunk857 ms287 ms
TTFT857 ms287 ms
Load time41.0 s0.7 s
Memory usage3.0 GB9.6 GB
Memory %19%30%

HW Fit Score Breakdown

qwen3:4b

Speed
34/50
TTFT
20/20
Memory
30/30

yi-coder:9b

Speed
39/50
TTFT
20/20
Memory
30/30

Quality

qwen3:4b

Reasoning
0/20
Coding
2/20
Instruction
2/20
Structured
0/15
Math
1/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

yi-coder:9b

Reasoning
12/20
Coding
16/20
Instruction
13/20
Structured
7/15
Math
7/15
Multilingual
7/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Weak Math: Weak Multilingual: Adequate
View qwen3:4b details | View yi-coder:9b 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