Back to leaderboard

qwen3.6-27b-mtp

LM-STUDIO GGUF

qwen35 · 27B · Q5_K_M

Excellent

Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Qwen3.8-27B-Ridge-3.7bpw_empero.ai:latest

OLLAMA GGUF

qwen35 · 27.3B · IQ2_M

Good

Aug 27, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
89 vs 75
Hardware Fit
85 vs 99
Quality Score
91 vs 64

Hardware

qwen3.6-27b-mtp Qwen3.8-27B-Ridge-…
MachineASUSMicro-Star International Co., Ltd. MS-7E51
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorAMD Ryzen 7 9700X 8-Core Processor
Cores1616
RAM31 GB31 GB
GPUNVIDIA GeForce RTX 4090, RaphaelNVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OScachyos rollingMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

qwen3.6-27b-mtp Qwen3.8-27B-Ridge-…
Tokens/sec74.960.3
First chunk3 ms154 ms
TTFT235 ms154 ms
Load timeN/A0.0 s
Memory usage21.5 GB11.0 GB
Memory %70%35%

HW Fit Score Breakdown

qwen3.6-27b-mtp

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

Qwen3.8-27B-Ridge-3.7bp…

Speed
50/50
TTFT
20/20
Memory
29/30

Quality

qwen3.6-27b-mtp

Reasoning
18/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

Qwen3.8-27B-Ridge-3.7bp…

Reasoning
20/20
Coding
17/20
Instruction
6/20
Structured
1/15
Math
14/15
Multilingual
6/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Adequate

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