Back to leaderboard

tinyllama-1.1b-chat-v1.0

LM-STUDIO GGUF

llama · 1.1B · Q3_K_M

Not Rec.

Mar 5, 2026 · Intel Core™ i5-5300U

huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
33 vs 88
Hardware Fit
76 vs 94
Quality Score
14 vs 85

Hardware

tinyllama-1.1b-cha… huihui-qwen3.6-35b…
MachineLENOVO 20BUS00700Gigabyte Technology Co., Ltd. B550M AORUS PRO
CPUIntel Core™ i5-5300UAMD Ryzen 5 5600X 6-Core Processor
Cores412
RAM16 GB47 GB
GPUIntel(R) HD Graphics 5500AD106 [GeForce RTX 4060 Ti]
OSMicrosoft Windows 10 Professionnel 10.0.19045cachyos rolling
Archx64x64
Power Modebalancedlow-power

Performance

tinyllama-1.1b-cha… huihui-qwen3.6-35b…
Tokens/sec9.939.8
First chunk3166 ms3 ms
TTFT3.2 s479 ms
Load timeN/AN/A
Memory usage0.5 GB24.4 GB
Memory %3%52%

HW Fit Score Breakdown

tinyllama-1.1b-chat-v1.0

Speed
32/50
TTFT
16/20
Memory
28/30

huihui-qwen3.6-35b-a3b-…

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

Quality

tinyllama-1.1b-chat-v1.0

Reasoning
2/20
Coding
1/20
Instruction
6/20
Structured
2/15
Math
1/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor

huihui-qwen3.6-35b-a3b-…

Reasoning
18/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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