Back to leaderboard

phi4-mini

OLLAMA GGUF
Not Rec.

Aug 28, 2026 · Intel Core™ i5-10210U

unsloth/qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q3_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
51 vs 85
Hardware Fit
46 vs 79
Quality Score
53 vs 88

Hardware

phi4-mini unsloth/qwen3.6-35…
MachineLENOVO 20U30029MBSystem manufacturer
CPUIntel Core™ i5-10210UAMD Ryzen 7 5800X 8-Core Processor
Cores816
RAM15 GB31 GB
GPUCometLake-U GT2 [UHD Graphics]Navi 44 [Radeon RX 9060 XT]
OSPop 24.04 LTSUbuntu 26.04.1 LTS
Archx64x64
Power Modeperformanceperformance

Performance

phi4-mini unsloth/qwen3.6-35…
Tokens/sec2.623.5
First chunk5406 ms54 ms
TTFT5.4 s457 ms
Load time27.4 sN/A
Memory usage4.6 GB18.3 GB
Memory %30%59%

HW Fit Score Breakdown

phi4-mini

Speed
6/50
TTFT
10/20
Memory
30/30

unsloth/qwen3.6-35b-a3b

Speed
38/50
TTFT
20/20
Memory
21/30

Quality

phi4-mini

Reasoning
11/20
Coding
9/20
Instruction
6/20
Structured
12/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong

unsloth/qwen3.6-35b-a3b

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View phi4-mini details | View unsloth/qwen3.6-35… 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