Back to leaderboard

hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ1_M

OLLAMA GGUF

qwen35 · 27.3B · unknown

Good

Aug 21, 2026 · AMD RYZEN AI MAX+ 395

microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score
68 vs 62
Hardware Fit
69 vs 99
Quality Score
67 vs 46

Hardware

hf.co/unsloth/Qwen… microsoft/phi-4-mi…
MachineAZW GTR ProMacBook Air
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM125 GB32 GB
GPURadeon 8060SApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modelow-powerbalanced

Performance

hf.co/unsloth/Qwen… microsoft/phi-4-mi…
Tokens/sec21.140.3
First chunk571 ms289 ms
TTFT571 ms289 ms
Load time4.9 sN/A
Memory usage22.7 GB2.0 GB
Memory %18%6%

HW Fit Score Breakdown

hf.co/unsloth/Qwen3.8-2…

Speed
20/50
TTFT
19/20
Memory
30/30

microsoft/phi-4-mini-re…

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

Quality

hf.co/unsloth/Qwen3.8-2…

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

microsoft/phi-4-mini-re…

Reasoning
7/20
Coding
6/20
Instruction
7/20
Structured
7/15
Math
12/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Adequate
View hf.co/unsloth/Qwen… 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