qwen3-coder-next:latest
OLLAMA GGUFqwen3next · 79.7B · Q4_K_M
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
ministral-3:3b
OLLAMA GGUFmistral3 · 3.8B · Q4_K_M
Mar 6, 2026 · Apple M4
Global Score
82 vs 71
Hardware Fit
71 vs 99
Quality Score
87 vs 59
Hardware
qwen3-coder-next:l… ministral-3:3b
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… ministral-3:3b
Tokens/sec34.542.2
First chunk262 ms189 ms
TTFT262 ms189 ms
Load time16.4 s1.2 s
Memory usage56.8 GB7.0 GB
Memory %46%22%
HW Fit Score Breakdown
qwen3-coder-next:latest
Speed
34/50
TTFT
20/20
Memory
17/30
ministral-3:3b
Speed
50/50
TTFT
20/20
Memory
29/30
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
ministral-3:3b
Reasoning
5/20
Coding
16/20
Instruction
11/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest