qwen3.8:latest
OLLAMA GGUFqwen35 · 27.3B · Q4_K_M
Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor
ministral-3:8b
OLLAMA GGUFmistral3 · 8.9B · Q4_K_M
Jun 25, 2026 · Apple M4 Pro
Global Score
68 vs 79
Hardware Fit
22 vs 98
Quality Score
88 vs 71
Hardware
qwen3.8:latest ministral-3:8b
MachineSystem manufacturerMac mini
CPUAMD Ryzen 9 5950X 16-Core ProcessorApple M4 Pro
Cores3212
RAM32 GB24 GB
GPUNVIDIA GeForce RTX 3090Apple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26300macOS 15.6.1
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3.8:latest ministral-3:8b
Tokens/sec10.041.4
First chunk1041 ms257 ms
TTFT14.3 s257 ms
Load time22.3 s5.2 s
Memory usage26.2 GB9.0 GB
Memory %82%38%
HW Fit Score Breakdown
qwen3.8:latest
Speed
12/50
TTFT
1/20
Memory
9/30
ministral-3:8b
Speed
50/50
TTFT
20/20
Memory
28/30
Quality
qwen3.8:latest
Reasoning
19/20
Coding
19/20
Instruction
10/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
ministral-3:8b
Reasoning
12/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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