Back to leaderboard

Mixtral-47B:47B

OLLAMA GGUF

llama · 46.7B · Q4_0

Not Rec.

Aug 19, 2026 · Intel Core™ i7-14700F

qwen3.5:0.8b

OLLAMA GGUF

qwen35 · 873.44M · Q8_0

Good

Mar 5, 2026 · Apple M1 Max

Global Score
55 vs 62
Hardware Fit
55 vs 100
Quality Score
55 vs 46

Hardware

Mixtral-47B:47B qwen3.5:0.8b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMacBook Pro
CPUIntel Core™ i7-14700FApple M1 Max
Cores2810
RAM64 GB32 GB
GPUNVIDIA GeForce RTX 5080Apple M1 Max
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

Mixtral-47B:47B qwen3.5:0.8b
Tokens/sec6.767.6
First chunk758 ms209 ms
TTFT758 ms209 ms
Load time12.1 s1.9 s
Memory usage25.5 GB2.6 GB
Memory %40%8%

HW Fit Score Breakdown

Mixtral-47B:47B

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

qwen3.5:0.8b

Speed
50/50
TTFT
20/20
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

qwen3.5:0.8b

Reasoning
9/20
Coding
4/20
Instruction
11/20
Structured
13/15
Math
3/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
View Mixtral-47B:47B details | View qwen3.5:0.8b details

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