Back to leaderboard

llama3.1:8b-instruct-q4_K_S

OLLAMA GGUF

llama · 8.0B · Q4_K_S

Good

Nov 22, 2026 · C1-Pro

qwen3.5-35b-a3b-t48-c8k:latest

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Aug 23, 2026 · Intel Xeon® E5-4650 v2

Global Score
70 vs 78
Hardware Fit
73 vs 51
Quality Score
68 vs 89

Hardware

llama3.1:8b-instru… qwen3.5-35b-a3b-t4…
Machine—Dell Inc. PowerEdge R820
CPUC1-ProIntel Xeon® E5-4650 v2
Cores080
RAM11 GB256 GB
GPUIntegrated / UnknownMicrosoft Remote Display Adapter, Microsoft Basic Display Adapter
OSunknown unknownMicrosoft Windows Server 2022 Datacenter 10.0.20348
Archarm64x64
Power Modeunknownbalanced

Performance

llama3.1:8b-instru… qwen3.5-35b-a3b-t4…
Tokens/sec6.57.1
First chunk950 ms997 ms
TTFT950 ms997 ms
Load time11.5 s45.4 s
Memory usage4.4 GB21.6 GB
Memory %38%8%

HW Fit Score Breakdown

llama3.1:8b-instruct-q4…

Speed
25/50
TTFT
20/20
Memory
28/30

qwen3.5-35b-a3b-t48-c8k…

Speed
6/50
TTFT
15/20
Memory
30/30

Quality

llama3.1:8b-instruct-q4…

Reasoning
11/20
Coding
17/20
Instruction
11/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

qwen3.5-35b-a3b-t48-c8k…

Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
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