Back to leaderboard

Mixtral-47B:47B

OLLAMA GGUF

llama · 46.7B · Q4_0

Not Rec.

Aug 19, 2026 · Intel Core™ i7-14700F

qwen3.6-35b-a3b-claude-4.7-opus-reasoning-distilled-apex

LM-STUDIO GGUF

qwen35moe · 35B

Not Rec.

Aug 19, 2026 · Apple M4 Max

Global Score
55 vs 88
Hardware Fit
55 vs 80
Quality Score
55 vs 92

Hardware

Mixtral-47B:47B qwen3.6-35b-a3b-cl…
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMacBook Pro
CPUIntel Core™ i7-14700FApple M4 Max
Cores2816
RAM64 GB128 GB
GPUNVIDIA GeForce RTX 5080Apple M4 Max
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced

Performance

Mixtral-47B:47B qwen3.6-35b-a3b-cl…
Tokens/sec6.776.7
First chunk758 ms29 ms
TTFT758 ms30.0 s
Load time12.1 sN/A
Memory usage25.5 GB23.9 GB
Memory %40%19%

HW Fit Score Breakdown

Mixtral-47B:47B

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

qwen3.6-35b-a3b-claude-…

Speed
50/50
TTFT
0/20
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

qwen3.6-35b-a3b-claude-…

Reasoning
19/20
Coding
18/20
Instruction
17/20
Structured
14/15
Math
14/15
Multilingual
10/10
Reasoning: Strong 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