Back to leaderboard

qwen3.8:27b

OLLAMA GGUF

qwen35 · 27.3B · Q4_K_M

Excellent

Oct 3, 2026 · Cortex-X925

granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

Global Score
84 vs 66
Hardware Fit
66 vs 87
Quality Score
92 vs 57

Hardware

qwen3.8:27b granite-3.3-2b-ins…
MachineNVIDIA NVIDIA_DGX_SparkMacBook Air
CPUCortex-X925Apple M4
Cores2010
RAM122 GB32 GB
GPUDevice 2e12Apple M4
OSUbuntu 24.04.5 LTSmacOS 26.3
Archarm64arm64
Power Modeperformancebalanced

Performance

qwen3.8:27b granite-3.3-2b-ins…
Tokens/sec29.418.3
First chunk306 ms541 ms
TTFT4.8 s541 ms
Load time5.3 sN/A
Memory usage16.2 GB4.7 GB
Memory %13%15%

HW Fit Score Breakdown

qwen3.8:27b

Speed
31/50
TTFT
5/20
Memory
30/30

granite-3.3-2b-instruct

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

Quality

qwen3.8:27b

Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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 qwen3.8:27b 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