Back to leaderboard

phi-3-mini-128k-instruct

LM-STUDIO MLX

phi3 · 4bit

Not Rec.

Mar 4, 2026 · Apple M4

qwen3.5-35b-a3b-t48-c8k:latest

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Aug 23, 2026 · Intel Xeon® E5-4650 v2

Global Score
38 vs 78
Hardware Fit
100 vs 51
Quality Score
12 vs 89

Hardware

phi-3-mini-128k-in… qwen3.5-35b-a3b-t4…
MachineMacBook AirDell Inc. PowerEdge R820
CPUApple M4Intel Xeon® E5-4650 v2
Cores1080
RAM32 GB256 GB
GPUApple M4Microsoft Remote Display Adapter, Microsoft Basic Display Adapter
OSmacOS 26.3Microsoft Windows Server 2022 Datacenter 10.0.20348
Archarm64x64
Power Modebalancedbalanced

Performance

phi-3-mini-128k-in… qwen3.5-35b-a3b-t4…
Tokens/sec44.07.1
First chunk384 ms997 ms
TTFT385 ms997 ms
Load timeN/A45.4 s
Memory usage2.0 GB21.6 GB
Memory %6%8%

HW Fit Score Breakdown

phi-3-mini-128k-instruct

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

qwen3.5-35b-a3b-t48-c8k…

Speed
6/50
TTFT
15/20
Memory
30/30

Quality

phi-3-mini-128k-instruct

Reasoning
3/20
Coding
2/20
Instruction
2/20
Structured
1/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

qwen3.5-35b-a3b-t48-c8k…

Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View phi-3-mini-128k-in… details | View qwen3.5-35b-a3b-t4… 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