Back to leaderboard

qwen3.5:35b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

Global Score
87 vs 82
Hardware Fit
86 vs 88
Quality Score
88 vs 80

Hardware

qwen3.5:35b unsloth-phi-4
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4Mac mini
CPUIntel Core™ i5-14400FApple M4 Pro
Cores1614
RAM32 GB64 GB
GPUNVIDIA GeForce RTX 5060 TiApple M4 Pro
OSMicrosoft Windows 11 Professionnel 10.0.26200macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3.5:35b unsloth-phi-4
Tokens/sec45.727.4
First chunk393 ms457 ms
TTFT393 ms457 ms
Load time22.9 sN/A
Memory usage21.6 GB7.7 GB
Memory %68%12%

HW Fit Score Breakdown

qwen3.5:35b

Speed
50/50
TTFT
20/20
Memory
16/30

unsloth-phi-4

Speed
38/50
TTFT
20/20
Memory
30/30

Quality

qwen3.5:35b

Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

unsloth-phi-4

Reasoning
15/20
Coding
19/20
Instruction
14/20
Structured
13/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:35b details | View unsloth-phi-4 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