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

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

Global Score
68 vs 65
Hardware Fit
69 vs 88
Quality Score
67 vs 55

Hardware

hf.co/unsloth/Qwen… qwen3.5-2b-mlx
MachineAZW GTR ProMac mini
CPUAMD RYZEN AI MAX+ 395Apple M4 Pro
Cores3214
RAM125 GB64 GB
GPURadeon 8060SApple M4 Pro
OSUbuntu 24.04.4 LTSmacOS 15.7.4
Archx64arm64
Power Modelow-powerbalanced

Performance

hf.co/unsloth/Qwen… qwen3.5-2b-mlx
Tokens/sec21.148.9
First chunk571 ms4208 ms
TTFT571 ms4.2 s
Load time4.9 sN/A
Memory usage22.7 GB1.6 GB
Memory %18%3%

HW Fit Score Breakdown

hf.co/unsloth/Qwen3.8-2…

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

qwen3.5-2b-mlx

Speed
50/50
TTFT
8/20
Memory
30/30

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

qwen3.5-2b-mlx

Reasoning
10/20
Coding
7/20
Instruction
13/20
Structured
14/15
Math
3/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View hf.co/unsloth/Qwen… details | View qwen3.5-2b-mlx 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