Back to leaderboard

qwen3.8:latest

OLLAMA GGUF

qwen35 · 27.3B · Q4_K_M

Good

Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor

granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

Global Score
68 vs 66
Hardware Fit
22 vs 87
Quality Score
88 vs 57

Hardware

qwen3.8:latest granite-3.3-2b-ins…
MachineSystem manufacturerMacBook Air
CPUAMD Ryzen 9 5950X 16-Core ProcessorApple M4
Cores3210
RAM32 GB32 GB
GPUNVIDIA GeForce RTX 3090Apple M4
OSMicrosoft Windows 11 Pro 10.0.26300macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3.8:latest granite-3.3-2b-ins…
Tokens/sec10.018.3
First chunk1041 ms541 ms
TTFT14.3 s541 ms
Load time22.3 sN/A
Memory usage26.2 GB4.7 GB
Memory %82%15%

HW Fit Score Breakdown

qwen3.8:latest

Speed
12/50
TTFT
1/20
Memory
9/30

granite-3.3-2b-instruct

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

Quality

qwen3.8:latest

Reasoning
19/20
Coding
19/20
Instruction
10/20
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:latest 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