Back to leaderboard

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

qwen3.5:122b-a10b

OLLAMA GGUF

qwen35moe · 125.1B · Q4_K_M

Excellent

Mar 12, 2026 · AMD RYZEN AI MAX+ 395

Global Score
78 vs 80
Hardware Fit
56 vs 52
Quality Score
87 vs 92

Hardware

qwen3.8-27b-mlx qwen3.5:122b-a10b
MachineMacBook ProAZW GTR Pro
CPUApple M1 ProAMD RYZEN AI MAX+ 395
Cores1032
RAM32 GB125 GB
GPUApple M1 ProRadeon 8060S
OSmacOS 15.6.1Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen3.8-27b-mlx qwen3.5:122b-a10b
Tokens/sec10.819.1
First chunk8 ms467 ms
TTFT2.6 s467 ms
Load timeN/A30.0 s
Memory usage21.0 GB89.3 GB
Memory %66%72%

HW Fit Score Breakdown

qwen3.8-27b-mlx

Speed
23/50
TTFT
16/20
Memory
17/30

qwen3.5:122b-a10b

Speed
18/50
TTFT
20/20
Memory
14/30

Quality

qwen3.8-27b-mlx

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

qwen3.5:122b-a10b

Reasoning
19/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.8-27b-mlx details | View qwen3.5:122b-a10b 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