qwen3-vl:2b
OLLAMA GGUFqwen3vl · 2.1B · Q4_K_M
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
rnj-1:8b
OLLAMA GGUFgemma3 · 8.3B · Q4_K_M
Aug 24, 2026 · Apple M1 Pro
Global Score
62 vs 80
Hardware Fit
99 vs 93
Quality Score
46 vs 74
Hardware
qwen3-vl:2b rnj-1:8b
MachineAZW GTR ProMacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M1 Pro
Cores3210
RAM125 GB16 GB
GPUAMD Radeon 8060SApple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archx64arm64
Power Modelow-powerbalanced
Performance
qwen3-vl:2b rnj-1:8b
Tokens/sec127.422.3
First chunk101 ms404 ms
TTFT630 ms404 ms
Load time5.9 s3.7 s
Memory usage33.2 GB8.3 GB
Memory %27%52%
HW Fit Score Breakdown
qwen3-vl:2b
Speed
50/50
TTFT
19/20
Memory
30/30
rnj-1:8b
Speed
49/50
TTFT
20/20
Memory
24/30
Quality
qwen3-vl:2b
Reasoning
7/20
Coding
0/20
Instruction
11/20
Structured
7/15
Math
13/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Strong Multilingual: Strong
rnj-1:8b
Reasoning
12/20
Coding
19/20
Instruction
15/20
Structured
5/15
Math
14/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Weak Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest