Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Excellent

Aug 18, 2026 · Apple M4 Max

nemotron3:33b

OLLAMA GGUF

nemotron_h_omni · 33.0B · Q4_K_M

Excellent

Jun 28, 2026 · AMD RYZEN AI MAX+ 395

Global Score
81 vs 96
Hardware Fit
68 vs 95
Quality Score
87 vs 97

Hardware

qwen/qwen3.8-27b nemotron3:33b
MachineMacBook ProAZW GTR Pro
CPUApple M4 MaxAMD RYZEN AI MAX+ 395
Cores1632
RAM128 GB125 GB
GPUApple M4 MaxRadeon 8060S
OSmacOS 26.5.2Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power

Performance

qwen/qwen3.8-27b nemotron3:33b
Tokens/sec16.462.7
First chunk5 ms372 ms
TTFT742 ms1.0 s
Load timeN/A13.1 s
Memory usage38.5 GB24.4 GB
Memory %30%20%

HW Fit Score Breakdown

qwen/qwen3.8-27b

Speed
18/50
TTFT
20/20
Memory
30/30

nemotron3:33b

Speed
50/50
TTFT
15/20
Memory
30/30

Quality

qwen/qwen3.8-27b

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

nemotron3:33b

Reasoning
19/20
Coding
18/20
Instruction
20/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen/qwen3.8-27b details | View nemotron3:33b 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