phi-1_5
LM-STUDIO GGUFphi2 · Q8_0
Mar 6, 2026 · Intel Core™ i5-5300U
mistral:latest
OLLAMA GGUFllama · 7.2B · Q4_K_M
May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor
Global Score
28 vs 73
Hardware Fit
66 vs 100
Quality Score
11 vs 62
Hardware
phi-1_5 mistral:latest
MachineLENOVO 20BUS00700Micro-Star International Co., Ltd. MS-7B79
CPUIntel Core™ i5-5300UAMD Ryzen 5 2600X Six-Core Processor
Cores412
RAM16 GB16 GB
GPUIntel(R) HD Graphics 5500NVIDIA GeForce GTX 1080
OSMicrosoft Windows 10 Professionnel 10.0.19045Microsoft Windows 11 Famille 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
phi-1_5 mistral:latest
Tokens/sec6.931.7
First chunk3040 ms102 ms
TTFT3.0 s102 ms
Load timeN/A14.3 s
Memory usage1.4 GB4.8 GB
Memory %9%30%
HW Fit Score Breakdown
phi-1_5
Speed
24/50
TTFT
16/20
Memory
26/30
mistral:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
phi-1_5
Reasoning
2/20
Coding
2/20
Instruction
3/20
Structured
0/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
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
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