Skip to content
Local AI Wizard
Your machine
Theme

SmolLM2-135M-Instruct

HuggingFaceTB · HuggingFaceTB/SmolLM2-135M-Instruct

Weights license: Apache 2.0 · code and components may use other terms

Reported by the publisher8 resultsHuggingFaceTB's model card · read 2026-10-25 · not ranked · see them
Memory needed~1 GBQ4 weights + working room, before the machine's reserve
Parameters0.1 BHub safetensors total
Repository updated2025-09-22A commit is not a release date

Quality

No comparable score

We track no public, comparable benchmark that covers this model yet. No score is inferred.

Reported by the publisher

8 results · HuggingFaceTB's model card · read 2026-10-25
IFEval (Average prompt/inst)
29.9
MT-Bench
19.8
HellaSwag
40.9
ARC (Average)
37.3
PIQA
66.3
MMLU (cloze)
29.3
BBH (3-shot)
28.23-shot
GSM8K (5-shot)
1.45-shot

Values as printed on the card, with the publisher's own settings (card section: Instruction model); column “SmolLM2-135M-Instruct”. Not comparable across publishers and not used in any ranking. Model card

Runs on

Fast memory holds it 119

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 119

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Not a measured fit or speed.

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

Runtime compatibility and tokens per second have not been measured for this entry. Published metadata and a memory estimate do not prove a successful local run.

Library in source: transformers

Choose my computer

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Task
text-generation
Architecture
LlamaForCausalLM
Library in source
transformers
Weight license
Apache 2.0
Commercial use
Allowed Apache License 2.0 text (SPDX) · read 2026-10-18license text
Context
8,192 tokensconfig.json max_position_embeddings; the card states no figuresource
Every stored field13 fields
Revision checked
12fd25f77366fa6b3b4b768ec3050bf629380bac
Architecture
LlamaForCausalLM
Library
transformers
Hub task tag
text-generation
Declared base models
HuggingFaceTB/SmolLM2-135M
Formats
onnx, safetensors
Access
Open download
Publisher kind
Official
Tensor evidence
floating-tensor-elements · 0.13B · BF16checked 2026-09-26
Repository created
2024-10-31creation is not the model's release
Repository updated
2025-09-22a commit is not a release date
Hub downloads (30 days) · likes
1,009,563 · 462this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Valid source snapshot: 2026-09-26. This source record has not received a complete technical review. Missing data remain unknown; a repository commit is not a model release date.