Back to leaderboard

llama3.3:70b

OLLAMA GGUF

llama · 70.6B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-X925

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score
73 vs 64
Hardware Fit
51 vs 69
Quality Score
83 vs 62

Hardware

llama3.3:70b qwen3.5:4b
MachineNVIDIA NVIDIA_DGX_SparkLENOVO 20U30029MB
CPUCortex-X925Intel Core™ i5-10210U
Cores208
RAM122 GB15 GB
GPUDevice 2e12CometLake-U GT2 [UHD Graphics]
OSUbuntu 24.04.4 LTSPop 24.04 LTS
Archarm64x64
Power Modeperformanceperformance

Performance

llama3.3:70b qwen3.5:4b
Tokens/sec4.67.4
First chunk560 ms1815 ms
TTFT560 ms1.8 s
Load time13.8 s10.9 s
Memory usage49.5 GB3.5 GB
Memory %41%23%

HW Fit Score Breakdown

llama3.3:70b

Speed
4/50
TTFT
20/20
Memory
27/30

qwen3.5:4b

Speed
19/50
TTFT
20/20
Memory
30/30

Quality

llama3.3:70b

Reasoning
17/20
Coding
18/20
Instruction
12/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

qwen3.5:4b

Reasoning
15/20
Coding
14/20
Instruction
6/20
Structured
12/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong
View llama3.3:70b details | View qwen3.5:4b 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