Back to leaderboard

llama-3.2-1b-instruct

LM-STUDIO GGUF

llama · 1B · Q4_K_M

Marginal

Mar 5, 2026 · Intel Core™ i5-5300U

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
50 vs 78
Hardware Fit
79 vs 51
Quality Score
37 vs 89

Hardware

llama-3.2-1b-instr… qwen3.5-35b-a3b-t4…
MachineLENOVO 20BUS00700Dell Inc. PowerEdge R820
CPUIntel Core™ i5-5300UIntel Xeon® E5-4650 v2
Cores480
RAM16 GB256 GB
GPUIntel(R) HD Graphics 5500Microsoft Remote Display Adapter, Microsoft Basic Display Adapter
OSMicrosoft Windows 10 Professionnel 10.0.19045Microsoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modebalancedbalanced

Performance

llama-3.2-1b-instr… qwen3.5-35b-a3b-t4…
Tokens/sec9.97.1
First chunk1668 ms997 ms
TTFT1.7 s997 ms
Load timeN/A45.4 s
Memory usage0.8 GB21.6 GB
Memory %5%8%

HW Fit Score Breakdown

llama-3.2-1b-instruct

Speed
32/50
TTFT
20/20
Memory
27/30

qwen3.5-35b-a3b-t48-c8k…

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

Quality

llama-3.2-1b-instruct

Reasoning
4/20
Coding
3/20
Instruction
10/20
Structured
10/15
Math
2/15
Multilingual
8/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor 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