Back to leaderboard

Mixtral-47B:47B

OLLAMA GGUF

llama · 46.7B · Q4_0

Not Rec.

Aug 19, 2026 · Intel Core™ i7-14700F

qwen/qwen3.6-35b-a3b

LM-STUDIO MLX

qwen3_5_moe · 35B · 4bit

Excellent

Jul 17, 2026 · Apple M5 Max

Global Score
55 vs 89
Hardware Fit
55 vs 97
Quality Score
55 vs 86

Hardware

Mixtral-47B:47B qwen/qwen3.6-35b-a3b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMacBook Pro
CPUIntel Core™ i7-14700FApple M5 Max
Cores2818
RAM64 GB64 GB
GPUNVIDIA GeForce RTX 5080Apple M5 Max
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 27.0
Archx64arm64
Power Modebalancedbalanced

Performance

Mixtral-47B:47B qwen/qwen3.6-35b-a3b
Tokens/sec6.7130.2
First chunk758 ms5 ms
TTFT758 ms135 ms
Load time12.1 sN/A
Memory usage25.5 GB26.6 GB
Memory %40%42%

HW Fit Score Breakdown

Mixtral-47B:47B

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

qwen/qwen3.6-35b-a3b

Speed
50/50
TTFT
20/20
Memory
27/30

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

qwen/qwen3.6-35b-a3b

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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