Back to leaderboard

smollm2-135m-instruct

LM-STUDIO GGUF

llama · 135M · Q4_K_M

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

qwen3.8:27b-bf16

OLLAMA GGUF

qwen35 · 27.3B · BF16

Excellent

Aug 22, 2026 · AMD EPYC 7713 64-Core Processor

Global Score
38 vs 85
Hardware Fit
98 vs 77
Quality Score
12 vs 88

Hardware

smollm2-135m-instr… qwen3.8:27b-bf16
MachineLENOVO 20BUS00700Dell Inc. PowerEdge XE8545
CPUIntel Core™ i5-5300UAMD EPYC 7713 64-Core Processor
Cores4128
RAM16 GB1007 GB
GPUIntel(R) HD Graphics 5500GA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB], Integrated Matrox G200eW3 Graphics Controller, GA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB]
OSMicrosoft Windows 10 Professionnel 10.0.19045Rocky Linux 8.10
Archx64x64
Power Modebalancedunknown

Performance

smollm2-135m-instr… qwen3.8:27b-bf16
Tokens/sec39.327.2
First chunk573 ms237 ms
TTFT573 ms237 ms
Load timeN/A43.8 s
Memory usage0.1 GB68.8 GB
Memory %1%7%

HW Fit Score Breakdown

smollm2-135m-instruct

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

qwen3.8:27b-bf16

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

Quality

smollm2-135m-instruct

Reasoning
2/20
Coding
1/20
Instruction
5/20
Structured
3/15
Math
0/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor

qwen3.8:27b-bf16

Reasoning
18/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View smollm2-135m-instr… details | View qwen3.8:27b-bf16 details

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