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

Ornith-1.5-35B-A3B-NVFP4-Q5K-mtp:latest

OLLAMA GGUF

qwen35moe · 35.5B · NVFP4

Excellent

Aug 23, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
51 vs 82
Hardware Fit
31 vs 81
Quality Score
60 vs 82

Hardware

llama3.3:70b-instr… Ornith-1.5-35B-A3B…
MachineDell Inc. Precision Tower 7910Micro-Star International Co., Ltd. MS-7E51
CPUIntel Xeon® E5-2637 v3AMD Ryzen 7 9700X 8-Core Processor
Cores1616
RAM96 GB31 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSMicrosoft Windows 10 Pro 10.0.19045Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

llama3.3:70b-instr… Ornith-1.5-35B-A3B…
Tokens/sec1.767.9
First chunk5553 ms216 ms
TTFT5.6 s216 ms
Load time0.4 s12.6 s
Memory usage50.3 GB24.1 GB
Memory %53%78%

HW Fit Score Breakdown

llama3.3:70b-instruct-q…

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

Ornith-1.5-35B-A3B-NVFP…

Speed
50/50
TTFT
20/20
Memory
11/30

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

Ornith-1.5-35B-A3B-NVFP…

Reasoning
14/20
Coding
19/20
Instruction
15/20
Structured
14/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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