mistral:latest
OLLAMA GGUFllama · 7.2B · Q4_K_M
May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor
qwen3.5:2b
OLLAMA GGUFqwen35 · 2.3B · Q8_0
Apr 29, 2026 · Intel Core™ i5-8350U
Global Score
73 vs 13
Hardware Fit
100 vs 41
Quality Score
62 vs 1
Hardware
mistral:latest qwen3.5:2b
MachineMicro-Star International Co., Ltd. MS-7B79LENOVO 20L7CTO1WW
CPUAMD Ryzen 5 2600X Six-Core ProcessorIntel Core™ i5-8350U
Cores128
RAM16 GB23 GB
GPUNVIDIA GeForce GTX 1080Kaby Lake-R GT2 [UHD Graphics 620]
OSMicrosoft Windows 11 Famille 10.0.26200Fedora Linux 43
Archx64x64
Power Modebalancedlow-power
Performance
mistral:latest qwen3.5:2b
Tokens/sec31.74.5
First chunk102 ms1413 ms
TTFT102 ms31.1 s
Load time14.3 s7.1 s
Memory usage4.8 GB3.8 GB
Memory %30%16%
HW Fit Score Breakdown
mistral:latest
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.5:2b
Speed
11/50
TTFT
0/20
Memory
30/30
Quality
mistral:latest
Reasoning
8/20
Coding
13/20
Instruction
16/20
Structured
12/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
qwen3.5:2b
Reasoning
0/20
Coding
0/20
Instruction
1/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
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