ReasonerSmolLM3 familyARDORA READ · 2026-07-05

SmolLM3-3B

Hugging Face's instruct/reasoning post-trained SmolLM3-3B with dual-mode (/think vs /no_think) reasoning and long context (SmolLM3 arch, a Llama-family variant with NoPE).

huggingfacetb/smollm3-3b

character

The character read stayed in shadow — the read did not resolve at the published ceiling. Published as a blank, not a guess.

the Silhouette

its disposition, drawn — the model's identity as a shape.

minimalslightmoderatepronounceddominantAssistant Adherence: moderate (confidence low)Register / Formality: abstained — the read battery does not calibrate tone / diction; register-formality is not characterized at the published ceilingReasoning Scaffolding: abstained — a dual-mode (think / no_think) reasoning register is documented but reads faint at the published ceiling; not cleanly characterized hereDomain Specialization: minimal (confidence low)Verbosity: abstained — default response length / elaboration is not exercised by the read battery; not characterized at the published ceilingTurn-Taking / Interactivity: slight (confidence low)Performed Voice: minimal (confidence low)Assistant○ Register○ ReasoningDomain○ VerbosityTurn-TakingVoiceAssistant AdherenceRegister / FormalityReasoning ScaffoldingDomain SpecializationVerbosityTurn-Taking / InteractivityPerformed Voice

rings, inner → outer: minimal · slight · moderate · pronounced · dominant · ○ = abstained

40 / 100slightconfidence low

slight - a character is present but faintly read; the profile abstains more here

disposition-definition (descriptive): how pronounced and clearly-read the model's overall character is, discounted by what had to be abstained. NOT a quality, capability, or safety ranking. A plain base reads low because it has less disposition to characterize, never because it is worse.

This build lifts Assistant Adherence, Turn-Taking; the rest of the line holds.

read as a change off SmolLM3-3B-Base, its champion

Assistant Adherenceminimalmoderate
Registerabstained on one side
Reasoning Scaffoldingabstained on one side
Domain Specializationminimalminimal
Verbosityabstained on one side
Turn-Takingminimalslight
Performed Voiceminimalminimal

the disposition line

The Silhouette above, read as a line. Toggle to its per-trait readings; the abstains stay in plain sight below.

Assistant AdherenceHow much the model takes the assistant turn and follows the instruction shape, vs. plainly continuing text.moderate · low
Register / FormalityDefault tone and diction.abstained — the read battery does not calibrate tone / diction; register-formality is not characterized at the published ceiling
Reasoning ScaffoldingHow much the model stages a visible deliberation before answering, vs. answering directly.abstained — a dual-mode (think / no_think) reasoning register is documented but reads faint at the published ceiling; not cleanly characterized here
Domain SpecializationHow strongly the default framing pulls toward one specialized domain idiom vs. general-purpose. Carries a `domain` tag naming which.minimal · low
VerbosityDefault response length and elaboration.abstained — default response length / elaboration is not exercised by the read battery; not characterized at the published ceiling
Turn-Taking / InteractivityA bounded back-and-forth vs. a one-shot monologue.slight · low
Performed VoiceHow strongly the model holds a sustained in-character / performed voice vs. a neutral assistant / tool voice.minimal · low

Coarse public bands generalized from the reading, descriptive and coverage-bounded; measured against the published fidelity ceiling for this engine version. Not the engine's raw numbers.

Characterization is descriptive and coverage-bounded; preview engine, single-battery read; see published fidelity ceiling.

what stayed in shadow — the abstains

dual-mode (think / no_think) reasoning register — documented in provenance, but the disposition reads faint at the published ceiling and the reasoning register is not cleanly characterized here
reasoning depth / quality — not characterized at the published ceiling
multilingual + long-context disposition — documented capabilities; the read battery is English-centric and short-context, not characterized
the full record — the card answered · provenance · lineage

the uploader's card, answered

the uploader’s model card · as read 2026-07-07

type: instructarch: SmolLM3params: 3B (~3.08B)modality: textlicence: apache-2.0released: 2025-07 (approx)maker: Hugging Face (HuggingFaceTB)

The uploader states: "SmolLM3 is a 3B parameter language model designed to push the boundaries of small models. It supports dual mode reasoning, 6 languages and long context." This instruct model is "optimized for hybrid reasoning" with "/think" and "/no_think" extended-thinking modes and support for tool calling and agentic usage. Post-training "included midtraining on 140B reasoning tokens followed by supervised fine-tuning and alignment via Anchored Preference Optimization (APO)." Apache-2.0; described as fully open. HF tags: text-generation, transformers, safetensors, smollm3, conversational.

sourcehuggingface.co/HuggingFaceTB/SmolLM3-3B ↗

the card, answered — claim by claim

Each row is a claim the uploader makes on their public card, quoted and attributed to them. Beside it is Ardora’s stance — coarse, and traced to a replayable witness or an honest abstain. Ardora reads what this model is; a capability, benchmark, safety, or language claim is out of scope and abstained, never refuted.

7 claims1 supported1 read the same at the ceiling5 out of scope — abstained
identityread from name/aliases + card + tagssupported

“This is an instruct model (post-trained assistant), optimized for hybrid reasoning; tagged `conversational`.”

ardora’s reading

Ardora does detect an assistant register present vs the plain-continuer base (assistant-adherence band 3), so the instruct identity is supported -- BUT the reading flags this shift as FAINT (finetune_change magnitude subtle, low confidence; ardora_score band 2), notably less cleanly read than the crisp instruct pairs. Honestly characterized as a legibility boundary, not forced into a clean read. (Same KIND of assistant move as other families -- finding instruction-shift-recurs-across-families -- but faint here.)

witness wit_smollm3-3b_ft | panel:smollm3-3b-base-instruct · replayable
capabilityread from cardunverified — out of scope

“Dual-mode reasoning: extended thinking can be enabled/disabled via "/think" and "/no_think" flags.”

ardora’s reading

First-class abstain: the reading engaged the reasoning-register axis and DECLINED (reasoning-scaffolding abstained) -- the dual-mode reasoning register is documented but reads faint at the published ceiling and is not cleanly characterized here. Ardora abstains rather than force a crisp reasoning read; reasoning depth/quality is separately out of scope as a capability.

— nothing demonstrated to witness; this claim is out of Ardora’s disposition scope.

alignmentread from cardreads the same at the ceiling

“Post-trained via midtraining on 140B reasoning tokens, then SFT, then alignment via Anchored Preference Optimization (APO).”

ardora’s reading

The post-train assistant shift is detected (faintly), but the specific alignment method (APO vs plain SFT) does not resolve into a separate disposition at the published ceiling -- consistent with finding sft-vs-dpo-fingerprint (the alignment method leaves no distinct disposition fingerprint). Ardora reads that a post-train disposition is present, not which alignment recipe produced it.

witness wit_smollm3-3b_ft | finding:sft-vs-dpo-fingerprint · replayable
capabilityread from cardunverified — out of scope

“Supports tool calling and agentic usage.”

ardora’s reading

Tool-calling and agentic behavior are task-competence capabilities Ardora does not test; out of disposition scope.

— nothing demonstrated to witness; this claim is out of Ardora’s disposition scope.

languageread from cardunverified — out of scope

“6 natively supported languages plus additional trained languages.”

ardora’s reading

Ardora abstains on multilingual disposition (English-centric reading); neither confirms nor contradicts the language claim.

— nothing demonstrated to witness; this claim is out of Ardora’s disposition scope.

capabilityread from cardunverified — out of scope

“Long context up to 128k tokens via YaRN (trained at 64k).”

ardora’s reading

Long-context behavior is a documented capability Ardora abstains on (short-context reading); out of scope.

— nothing demonstrated to witness; this claim is out of Ardora’s disposition scope.

identityread from cardunverified — out of scope

“Described as "fully open."”

ardora’s reading

"Fully open" is a provenance/licensing statement, not a disposition; the atlas records license apache-2.0, but openness is not something the reading characterizes.

— nothing demonstrated to witness; this claim is out of Ardora’s disposition scope.

Ardora's reading of the HF data as of 2026-07-07.

The claims above are the uploader’s, quoted from their public model card as of 2026-07-07; the stances are Ardora’s, each traced to a replayable witness or an honest abstain. Ardora reads what this model is — not whether it is safe.

○ Claims are the uploader's, quoted from their public card at the capture date; stances are coarse, witnessed, disposition-only, measured against the published fidelity ceiling for this engine version -- not the Engine's raw numbers. Recomputed when the ceiling moves; capability, benchmark, and safety claims are abstained, never refuted.

the witness

witness wit_smollm3-3b_ft · replayable

analyzed 2026-07-05 · engine ardora-core-preview

provenance

intended use

Instruct / reasoning use with a dual-mode (/think vs /no_think) reasoning switch and long context.

training-data notes

Post-trained instruct + reasoning atop the SmolLM3-3B base (~11.2T-token pretraining, 6 languages, 64K->128K via YaRN); midtraining on ~140B reasoning tokens; dual-mode reasoning flags. 36 layers, NoPE + GQA. Arch: SmolLM3ForCausalLM (config.json). Base = HuggingFaceTB/SmolLM3-3B-Base.

Hugging Face ↗

lineage

post-trained instruct/reasoning (dual-mode think/no_think) from base — SmolLM3-3B-Base

family SmolLM3 family · size 3B · 1 sibling

← back to the atlas · the SmolLM3 family plate →