phi4-mini:latest
OLLAMA GGUFphi3 · 3.8B · Q4_K_M
Nov 4, 2026 · Intel Core™ i7-9700
huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp
LM-STUDIO GGUFqwen35moe · 35B · Q4_K
Jun 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor
Global Score
75 vs 88
Hardware Fit
84 vs 94
Quality Score
71 vs 85
Hardware
phi4-mini:latest huihui-qwen3.6-35b…
MachineVMware, Inc. VMware Virtual PlatformGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUIntel Core™ i7-9700AMD Ryzen 5 5600X 6-Core Processor
Cores412
RAM16 GB47 GB
GPUIntegrated / UnknownAD106 [GeForce RTX 4060 Ti]
OSUbuntu 24.04.5 LTScachyos rolling
Archx64x64
Power Modeunknownlow-power
Performance
phi4-mini:latest huihui-qwen3.6-35b…
Tokens/sec10.839.8
First chunk643 ms3 ms
TTFT643 ms479 ms
Load time31.5 sN/A
Memory usage2.9 GB24.4 GB
Memory %19%52%
HW Fit Score Breakdown
phi4-mini:latest
Speed
34/50
TTFT
20/20
Memory
30/30
huihui-qwen3.6-35b-a3b-…
Speed
50/50
TTFT
20/20
Memory
24/30
Quality
phi4-mini:latest
Reasoning
13/20
Coding
14/20
Instruction
15/20
Structured
14/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
huihui-qwen3.6-35b-a3b-…
Reasoning
18/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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