Mixtral-47B:47B
OLLAMA GGUFllama · 46.7B · Q4_0
Aug 19, 2026 · Intel Core™ i7-14700F
qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jun 19, 2026 · Apple M4 Max
Global Score
55 vs 89
Hardware Fit
55 vs 96
Quality Score
55 vs 86
Hardware
Mixtral-47B:47B qwen3-coder:30b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMacBook Pro
CPUIntel Core™ i7-14700FApple M4 Max
Cores2816
RAM64 GB64 GB
GPUNVIDIA GeForce RTX 5080Apple M4 Max
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 26.5.1
Archx64arm64
Power Modebalancedbalanced
Performance
Mixtral-47B:47B qwen3-coder:30b
Tokens/sec6.789.9
First chunk758 ms188 ms
TTFT758 ms188 ms
Load time12.1 s4.0 s
Memory usage25.5 GB30.2 GB
Memory %40%47%
HW Fit Score Breakdown
Mixtral-47B:47B
Speed
7/50
TTFT
20/20
Memory
28/30
qwen3-coder:30b
Speed
50/50
TTFT
20/20
Memory
26/30
Quality
Mixtral-47B:47B
Reasoning
9/20
Coding
14/20
Instruction
6/20
Structured
12/15
Math
7/15
Multilingual
7/10
Reasoning: Weak Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Adequate
qwen3-coder:30b
Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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