Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Excellent

Aug 18, 2026 · Apple M4 Max

qwen3.6-35b-a3b-mtp

LM-STUDIO GGUF

qwen35moe · 35B · IQ3_XXS

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score
87 vs 77
Hardware Fit
83 vs 55
Quality Score
88 vs 86

Hardware

qwen/qwen3.8-27b qwen3.6-35b-a3b-mtp
MachineMacBook ProDocker Container
CPUApple M4 MaxIntel Gen Intel® Core™ i9-11900H
Cores1616
RAM128 GB15 GB
GPUApple M4 MaxTigerLake-H GT1 [UHD Graphics]
OSmacOS 26.5.2Ubuntu 26.04 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen/qwen3.8-27b qwen3.6-35b-a3b-mtp
Tokens/sec29.19.2
First chunk9 ms38 ms
TTFT650 ms4.7 s
Load timeN/A46.7 s
Memory usage21.0 GB0.0 GB
Memory %16%0%

HW Fit Score Breakdown

qwen/qwen3.8-27b

Speed
33/50
TTFT
20/20
Memory
30/30

qwen3.6-35b-a3b-mtp

Speed
16/50
TTFT
9/20
Memory
30/30

Quality

qwen/qwen3.8-27b

Reasoning
18/20
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

qwen3.6-35b-a3b-mtp

Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen/qwen3.8-27b details | View qwen3.6-35b-a3b-mtp 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