Back to leaderboard

qwen3-vl:4b-instruct

OLLAMA GGUF

qwen3vl · 4.4B · Q4_K_M

Excellent

Apr 20, 2026 · Apple M2 Max

qwen2.5-coder:7b

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Good

Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K

Global Score
83 vs 68
Hardware Fit
96 vs 59
Quality Score
78 vs 72

Hardware

qwen3-vl:4b-instruct qwen2.5-coder:7b
MachineMac StudioASUS
CPUApple M2 MaxIntel Gen Intel® Core™ i7-13700K
Cores1224
RAM96 GB64 GB
GPUApple M2 MaxNVIDIA GeForce RTX 3070
OSmacOS 26.1Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown

Performance

qwen3-vl:4b-instruct qwen2.5-coder:7b
Tokens/sec90.634.4
First chunk159 ms1991 ms
TTFT159 ms2.0 s
Load time5.8 s40.6 s
Memory usage42.5 GB5.0 GB
Memory %44%8%

HW Fit Score Breakdown

qwen3-vl:4b-instruct

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

qwen2.5-coder:7b

Speed
38/50
TTFT
12/20
Memory
9/30

Quality

qwen3-vl:4b-instruct

Reasoning
14/20
Coding
16/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

qwen2.5-coder:7b

Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3-vl:4b-instruct details | View qwen2.5-coder:7b 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