Back to leaderboard

qwen3.8:27b

OLLAMA GGUF

qwen35 · 27.3B · Q4_K_M

Excellent

Oct 3, 2026 · Cortex-X925

phi4-mini:latest

OLLAMA GGUF

phi3 · 3.8B · Q4_K_M

Good

Nov 4, 2026 · Intel Core™ i7-9700

Global Score
84 vs 75
Hardware Fit
66 vs 84
Quality Score
92 vs 71

Hardware

qwen3.8:27b phi4-mini:latest
MachineNVIDIA NVIDIA_DGX_SparkVMware, Inc. VMware Virtual Platform
CPUCortex-X925Intel Core™ i7-9700
Cores204
RAM122 GB16 GB
GPUDevice 2e12Integrated / Unknown
OSUbuntu 24.04.5 LTSUbuntu 24.04.5 LTS
Archarm64x64
Power Modeperformanceunknown

Performance

qwen3.8:27b phi4-mini:latest
Tokens/sec29.410.8
First chunk306 ms643 ms
TTFT4.8 s643 ms
Load time5.3 s31.5 s
Memory usage16.2 GB2.9 GB
Memory %13%19%

HW Fit Score Breakdown

qwen3.8:27b

Speed
31/50
TTFT
5/20
Memory
30/30

phi4-mini:latest

Speed
34/50
TTFT
20/20
Memory
30/30

Quality

qwen3.8:27b

Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

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

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest