Back to leaderboard

meta-llama-3.1-8b-instruct

llama · 8B · 4bit

Good

Mar 3, 2026 · Apple M4

qwen3.5:0.8b

qwen35 · 873.44M · Q8_0

Good

Mar 2, 2026 · Apple M4

Global Score
76 vs 65
Hardware Fit
95 vs 99
Quality Score
68 vs 51

Hardware

meta-llama-3.1-8b-… qwen3.5:0.8b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

meta-llama-3.1-8b-… qwen3.5:0.8b
Tokens/sec21.648.2
TTFT512 ms195 ms
Load time0.0 s1.0 s
Memory usage0.0 GB2.5 GB
Memory %0%8%

HW Fit Score Breakdown

meta-llama-3.1-8b-instr…

Speed
35/40
TTFT
30/30
Memory
30/30

qwen3.5:0.8b

Speed
40/40
TTFT
30/30
Memory
29/30

Quality

meta-llama-3.1-8b-instr…

Reasoning
11/20
Coding
15/20
Instruction
14/20
Structured
14/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

qwen3.5:0.8b

Reasoning
9/20
Coding
6/20
Instruction
11/20
Structured
13/15
Math
5/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Adequate
View meta-llama-3.1-8b-… details | View qwen3.5:0.8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running