Back to leaderboard

Mixtral-47B:47B

OLLAMA GGUF

llama · 46.7B · Q4_0

Not Rec.

Aug 19, 2026 · Intel Core™ i7-14700F

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

Global Score
55 vs 65
Hardware Fit
55 vs 88
Quality Score
55 vs 55

Hardware

Mixtral-47B:47B qwen3.5-2b-mlx
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMac mini
CPUIntel Core™ i7-14700FApple M4 Pro
Cores2814
RAM64 GB64 GB
GPUNVIDIA GeForce RTX 5080Apple M4 Pro
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced

Performance

Mixtral-47B:47B qwen3.5-2b-mlx
Tokens/sec6.748.9
First chunk758 ms4208 ms
TTFT758 ms4.2 s
Load time12.1 sN/A
Memory usage25.5 GB1.6 GB
Memory %40%3%

HW Fit Score Breakdown

Mixtral-47B:47B

Speed
7/50
TTFT
20/20
Memory
28/30

qwen3.5-2b-mlx

Speed
50/50
TTFT
8/20
Memory
30/30

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

qwen3.5-2b-mlx

Reasoning
10/20
Coding
7/20
Instruction
13/20
Structured
14/15
Math
3/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

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