Back to leaderboard

llama3.1:8b

llama · 8.0B · Q4_K_M

Not Rec.

Feb 28, 2026 · Apple M4 Pro

qwen3:1.7b

qwen3 · 2.0B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

Global Score
64 vs 70
Hardware Fit
56 vs 87
Quality Score
70 vs 59

Hardware

llama3.1:8b qwen3:1.7b
MachineMac Mini—
CPUApple M4 ProApple M4
Cores1410
RAM64 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 15.7.4macOS 26.3
Archarm64arm64
Power Modeunknownbalanced

Performance

llama3.1:8b qwen3:1.7b
Tokens/sec5.537.9
TTFT1.4 s3.1 s
Load time3.7 s1.2 s
Memory usage28.6 GB4.9 GB
Memory %45%15%

HW Fit Score Breakdown

llama3.1:8b

Speed
5/40
TTFT
22/30
Memory
29/30

qwen3:1.7b

Speed
40/40
TTFT
17/30
Memory
30/30

Quality

llama3.1:8b

Reasoning
12/20
Coding
17/20
Instruction
14/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

qwen3:1.7b

Reasoning
16/20
Coding
0/20
Instruction
13/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View llama3.1:8b details | View qwen3:1.7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running