Back to leaderboard

unsloth/qwen3.5-9b@q4_k_m

LM-STUDIO GGUF

qwen35 · 9B · Q4_K_M

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

Global Score
73 vs 64
Hardware Fit
52 vs 100
Quality Score
82 vs 48

Hardware

unsloth/qwen3.5-9b… microsoft/phi-4-mi…
MachineDocker ContainerMac mini
CPUIntel Gen Intel® Core™ i9-11900HApple M4 Pro
Cores1614
RAM15 GB64 GB
GPUTigerLake-H GT1 [UHD Graphics]Apple M4 Pro
OSUbuntu 26.04 LTSmacOS 15.7.4
Archx64arm64
Power Modeperformancebalanced

Performance

unsloth/qwen3.5-9b… microsoft/phi-4-mi…
Tokens/sec6.590.3
First chunk13 ms198 ms
TTFT4.1 s198 ms
Load time10.8 sN/A
Memory usage2.2 GB2.0 GB
Memory %14%3%

HW Fit Score Breakdown

unsloth/qwen3.5-9b@q4_k_m

Speed
11/50
TTFT
11/20
Memory
30/30

microsoft/phi-4-mini-re…

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

Quality

unsloth/qwen3.5-9b@q4_k_m

Reasoning
15/20
Coding
17/20
Instruction
16/20
Structured
15/15
Math
9/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

microsoft/phi-4-mini-re…

Reasoning
7/20
Coding
7/20
Instruction
7/20
Structured
7/15
Math
13/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Adequate
View unsloth/qwen3.5-9b… details | View microsoft/phi-4-mi… details

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