Back to leaderboard

qwen3-coder-next:latest

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Excellent

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

Global Score
82 vs 66
Hardware Fit
71 vs 87
Quality Score
87 vs 57

Hardware

qwen3-coder-next:l… granite-3.3-2b-ins…
MachineAZW GTR ProMacBook Air
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM125 GB32 GB
GPUAMD Radeon 8060SApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced

Performance

qwen3-coder-next:l… granite-3.3-2b-ins…
Tokens/sec34.518.3
First chunk262 ms541 ms
TTFT262 ms541 ms
Load time16.4 sN/A
Memory usage56.8 GB4.7 GB
Memory %46%15%

HW Fit Score Breakdown

qwen3-coder-next:latest

Speed
34/50
TTFT
20/20
Memory
17/30

granite-3.3-2b-instruct

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

Quality

qwen3-coder-next:latest

Reasoning
18/20
Coding
18/20
Instruction
13/20
Structured
15/15
Math
13/15
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-coder-next:l… 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