Back to leaderboard

phi-3.5-mini-instruct

LM-STUDIO MLX

phi3 · 4bit

Marginal

Mar 4, 2026 · Apple M4

Qwen3.8-27B-Ridge-3.7bpw_empero.ai:latest

OLLAMA GGUF

qwen35 · 27.3B · IQ2_M

Good

Aug 27, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
55 vs 75
Hardware Fit
100 vs 99
Quality Score
36 vs 64

Hardware

phi-3.5-mini-instr… Qwen3.8-27B-Ridge-…
MachineMacBook AirMicro-Star International Co., Ltd. MS-7E51
CPUApple M4AMD Ryzen 7 9700X 8-Core Processor
Cores1016
RAM32 GB31 GB
GPUApple M4NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

phi-3.5-mini-instr… Qwen3.8-27B-Ridge-…
Tokens/sec43.460.3
First chunk359 ms154 ms
TTFT359 ms154 ms
Load timeN/A0.0 s
Memory usage2.0 GB11.0 GB
Memory %6%35%

HW Fit Score Breakdown

phi-3.5-mini-instruct

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

Qwen3.8-27B-Ridge-3.7bp…

Speed
50/50
TTFT
20/20
Memory
29/30

Quality

phi-3.5-mini-instruct

Reasoning
11/20
Coding
4/20
Instruction
7/20
Structured
1/15
Math
7/15
Multilingual
6/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Weak Multilingual: Adequate

Qwen3.8-27B-Ridge-3.7bp…

Reasoning
20/20
Coding
17/20
Instruction
6/20
Structured
1/15
Math
14/15
Multilingual
6/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Adequate
View phi-3.5-mini-instr… details | View Qwen3.8-27B-Ridge-… 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