Back to leaderboard

qwen3.8-27b-uncensored-ymq-mtp

LM-STUDIO GGUF

qwen35 · 27B

Excellent

Sep 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor

qwen3-coder-30b-a3b-instruct-mlx

LM-STUDIO MLX

qwen3_moe · 30B · 4bit

Excellent

Oct 20, 2026 · Apple M1 Pro

Global Score
84 vs 87
Hardware Fit
81 vs 85
Quality Score
85 vs 88

Hardware

qwen3.8-27b-uncens… qwen3-coder-30b-a3…
MachineGigabyte Technology Co., Ltd. X570 AORUS PROMacBook Pro
CPUAMD Ryzen 5 5600X 6-Core ProcessorApple M1 Pro
Cores1210
RAM32 GB32 GB
GPUNVIDIA GeForce RTX 5070 TiApple M1 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 15.6.1
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3.8-27b-uncens… qwen3-coder-30b-a3…
Tokens/sec18.345.7
First chunk9 ms17 ms
TTFT522 ms390 ms
Load time7.7 sN/A
Memory usage14.9 GB22.4 GB
Memory %47%70%

HW Fit Score Breakdown

qwen3.8-27b-uncensored-…

Speed
35/50
TTFT
20/20
Memory
26/30

qwen3-coder-30b-a3b-ins…

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

Quality

qwen3.8-27b-uncensored-…

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

qwen3-coder-30b-a3b-ins…

Reasoning
15/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.8-27b-uncens… details | View qwen3-coder-30b-a3… 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