phi4:latest
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
qwen3.5-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · IQ3_XXS
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
Global Score
85 vs 80
Hardware Fit
100 vs 62
Quality Score
79 vs 88
Hardware
phi4:latest qwen3.5-35b-a3b
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4Docker Container
CPUIntel Core™ i5-14400FIntel Gen Intel® Core™ i9-11900H
Cores1616
RAM32 GB15 GB
GPUNVIDIA GeForce RTX 5060 TiTigerLake-H GT1 [UHD Graphics]
OSMicrosoft Windows 11 Professionnel 10.0.26200Ubuntu 26.04 LTS
Archx64x64
Power Modebalancedperformance
Performance
phi4:latest qwen3.5-35b-a3b
Tokens/sec38.310.6
First chunk72 ms52 ms
TTFT72 ms3.2 s
Load time6.2 s7.6 s
Memory usage9.1 GB1.1 GB
Memory %29%7%
HW Fit Score Breakdown
phi4:latest
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.5-35b-a3b
Speed
19/50
TTFT
13/20
Memory
30/30
Quality
phi4:latest
Reasoning
18/20
Coding
19/20
Instruction
12/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
qwen3.5-35b-a3b
Reasoning
16/20
Coding
18/20
Instruction
18/20
Structured
15/15
Math
11/15
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