ministral-3:8b
OLLAMA GGUFmistral3 · 8.9B · Q4_K_M
Aug 25, 2026 · Apple M1 Pro
qwen3-next:80b-a3b-instruct-q4_K_M
OLLAMA GGUFqwen3next · 79.7B · Q4_K_M
Aug 1, 2026 · Intel Xeon® E5-2637 v3
Global Score
72 vs 80
Hardware Fit
71 vs 54
Quality Score
72 vs 91
Hardware
ministral-3:8b qwen3-next:80b-a3b…
MachineMacBook ProDell Inc. Precision Tower 7910
CPUApple M1 ProIntel Xeon® E5-2637 v3
Cores1016
RAM16 GB96 GB
GPUApple M1 ProNVIDIA GeForce RTX 5060 Ti
OSmacOS 26.6.2Microsoft Windows 10 Pro 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
ministral-3:8b qwen3-next:80b-a3b…
Tokens/sec19.814.9
First chunk269 ms1808 ms
TTFT269 ms1.8 s
Load time10.7 s95.0 s
Memory usage13.7 GB48.0 GB
Memory %86%50%
HW Fit Score Breakdown
ministral-3:8b
Speed
44/50
TTFT
20/20
Memory
7/30
qwen3-next:80b-a3b-inst…
Speed
16/50
TTFT
13/20
Memory
25/30
Quality
ministral-3:8b
Reasoning
12/20
Coding
18/20
Instruction
13/20
Structured
13/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
qwen3-next:80b-a3b-inst…
Reasoning
18/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong 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