Back to leaderboard

qwen3.8:27b

OLLAMA GGUF

qwen35 · 27.3B · Q4_K_M

Excellent

Aug 15, 2026 · AMD RYZEN AI MAX+ 395

hf.co/unsloth/gemma-4-E4B-it-GGUF:Q4_K_M

OLLAMA GGUF

gemma4 · 7.52B · unknown

Excellent

Aug 24, 2026 · Apple M1 Pro

Global Score
80 vs 87
Hardware Fit
66 vs 100
Quality Score
86 vs 82

Hardware

qwen3.8:27b hf.co/unsloth/gemm…
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

qwen3.8:27b hf.co/unsloth/gemm…
Tokens/sec18.435.0
First chunk587 ms204 ms
TTFT587 ms204 ms
Load time7.4 s3.9 s
Memory usage17.4 GB4.9 GB
Memory %14%31%

HW Fit Score Breakdown

qwen3.8:27b

Speed
17/50
TTFT
19/20
Memory
30/30

hf.co/unsloth/gemma-4-E…

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

Quality

qwen3.8:27b

Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

hf.co/unsloth/gemma-4-E…

Reasoning
14/20
Coding
18/20
Instruction
16/20
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