Back to leaderboard

llama3.3:70b-instruct-q4_K_M

OLLAMA GGUF

llama · 70.6B · Q4_K_M

Not Rec.

Aug 20, 2026 · Intel Xeon® E5-2637 v3

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor

Global Score
51 vs 85
Hardware Fit
31 vs 78
Quality Score
60 vs 88

Hardware

llama3.3:70b-instr… Kimi-48B:48B
MachineDell Inc. Precision Tower 7910HP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUIntel Xeon® E5-2637 v3AMD Ryzen 9 9955HX3D 16-Core Processor
Cores1632
RAM96 GB31 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060AMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSMicrosoft Windows 10 Pro 10.0.19045Microsoft Windows 11 Home 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

llama3.3:70b-instr… Kimi-48B:48B
Tokens/sec1.742.3
First chunk5553 ms718 ms
TTFT5.6 s718 ms
Load time0.4 s28.5 s
Memory usage50.3 GB25.8 GB
Memory %53%83%

HW Fit Score Breakdown

llama3.3:70b-instruct-q…

Speed
2/50
TTFT
5/20
Memory
24/30

Kimi-48B:48B

Speed
50/50
TTFT
20/20
Memory
8/30

Quality

llama3.3:70b-instruct-q…

Reasoning
17/20
Coding
6/20
Instruction
6/20
Structured
11/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Weak Instruction Following: Weak Structured Output: Adequate Math: Adequate Multilingual: Strong

Kimi-48B:48B

Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
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