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

hf.co/lmstudio-community/gemma-4-E4B-it-GGUF:Q6_K

OLLAMA GGUF

gemma4 · 7.52B · unknown

Excellent

Aug 23, 2026 · Apple M1 Pro

Global Score
68 vs 88
Hardware Fit
69 vs 100
Quality Score
67 vs 83

Hardware

hf.co/unsloth/Qwen… hf.co/lmstudio-com…
MachineAZW GTR ProMacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M1 Pro
Cores3210
RAM125 GB16 GB
GPURadeon 8060SApple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archx64arm64
Power Modelow-powerbalanced

Performance

hf.co/unsloth/Qwen… hf.co/lmstudio-com…
Tokens/sec21.134.6
First chunk571 ms210 ms
TTFT571 ms210 ms
Load time4.9 s4.0 s
Memory usage22.7 GB3.9 GB
Memory %18%25%

HW Fit Score Breakdown

hf.co/unsloth/Qwen3.8-2…

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

hf.co/lmstudio-communit…

Speed
50/50
TTFT
20/20
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

hf.co/lmstudio-communit…

Reasoning
14/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

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