Back to leaderboard

qwen3.6-27b-mtp-pi-reasoning

LM-STUDIO GGUF

qwen35 · 27B · Q4_K_M

Excellent

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

granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

Global Score
85 vs 66
Hardware Fit
80 vs 87
Quality Score
87 vs 57

Hardware

qwen3.6-27b-mtp-pi… granite-3.3-2b-ins…
MachineASUSMacBook Air
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorApple M4
Cores1610
RAM31 GB32 GB
GPUNVIDIA GeForce RTX 4090, RaphaelApple M4
OScachyos rollingmacOS 26.3
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen3.6-27b-mtp-pi… granite-3.3-2b-ins…
Tokens/sec78.518.3
First chunk5 ms541 ms
TTFT198 ms541 ms
Load timeN/AN/A
Memory usage24.6 GB4.7 GB
Memory %81%15%

HW Fit Score Breakdown

qwen3.6-27b-mtp-pi-reas…

Speed
50/50
TTFT
20/20
Memory
10/30

granite-3.3-2b-instruct

Speed
37/50
TTFT
20/20
Memory
30/30

Quality

qwen3.6-27b-mtp-pi-reas…

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

granite-3.3-2b-instruct

Reasoning
10/20
Coding
10/20
Instruction
14/20
Structured
14/15
Math
2/15
Multilingual
7/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
View qwen3.6-27b-mtp-pi… details | View granite-3.3-2b-ins… 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