This is Hugging Face's SmolLM3 3B model in MLC format q4f16_1.
It supports text generation in WebLLM.
The package context window is 65,536 tokens, with a prefill chunk size of 1,024. The proposed WebLLM record defaults to 4,096 tokens to limit memory use.
The q4f16_1 variant requires WebGPU's shader-f16 feature.
Matching WebGPU candidates use v0_2_87 and web-runtime 0.28.0-dev2; see library provenance.
Reasoning is on (the HF default). Turning it off needs a package generated with --conv-template smollm3_nothink; enable_thinking does not apply. The /think, /no_think and /system_override system-message switches of the HF template have no effect.
The HF template writes the current date into the system prompt. This package's template omits that line.
Sampling defaults come from the upstream generation_config.json: temperature 0.6, top_p 0.95.
a07cc9a04f16.be03dc94b001; used for weight conversion; the local Metal timer patch is recorded in the build information.5e824377af7f.Weights were converted with the sources above; WebGPU libraries were compiled separately with the source revisions in the linked library provenance.
With the conversion toolchain above installed and the pinned HF revision downloaded:
mlc_llm convert_weight hf/SmolLM3-3B --quantization q4f16_1 --device cpu -o dist/SmolLM3-3B-q4f16_1-MLC
mlc_llm gen_config hf/SmolLM3-3B --quantization q4f16_1 --conv-template smollm3 --context-window-size 65536 --prefill-chunk-size 1024 -o dist/SmolLM3-3B-q4f16_1-MLC
These are equivalent regeneration commands. The shipped configuration was retained from the original generation and adjusted to the maximum context and 1,024-token chunk; its SHA256 is recorded below in the build information.
mlc-build-info.json records the full revisions and source weight checksums.
See the upstream model card for model capabilities, evaluations, and limitations, and the WebLLM documentation for runtime usage.
params_shard_0.bin 131 MBparams_shard_10.bin 33 MBparams_shard_12.bin 33 MBparams_shard_13.bin 33 MBparams_shard_15.bin 33 MBparams_shard_16.bin 33 MBparams_shard_18.bin 33 MBparams_shard_19.bin 33 MBparams_shard_21.bin 33 MBparams_shard_22.bin 33 MBparams_shard_24.bin 33 MBparams_shard_25.bin 33 MBparams_shard_27.bin 33 MBparams_shard_28.bin 33 MBparams_shard_30.bin 33 MBparams_shard_31.bin 33 MBparams_shard_36.bin 33 MBparams_shard_37.bin 33 MBparams_shard_39.bin 33 MBparams_shard_40.bin 33 MBparams_shard_42.bin 33 MBparams_shard_43.bin 33 MBparams_shard_45.bin 33 MBparams_shard_49.bin 33 MBparams_shard_50.bin 33 MBparams_shard_52.bin 33 MBparams_shard_53.bin 33 MBparams_shard_55.bin 33 MBparams_shard_56.bin 33 MBparams_shard_6.bin 33 MBparams_shard_7.bin 33 MBparams_shard_9.bin 33 MBparams_shard_2.bin 32 MBparams_shard_34.bin 30 MBparams_shard_4.bin 27 MBparams_shard_47.bin 23 MBparams_shard_1.bin 23 MBparams_shard_11.bin 23 MBparams_shard_14.bin 23 MBparams_shard_17.bin 23 MBparams_shard_20.bin 23 MBparams_shard_23.bin 23 MBparams_shard_26.bin 23 MBparams_shard_29.bin 23 MBparams_shard_3.bin 23 MBparams_shard_32.bin 23 MBparams_shard_33.bin 23 MBparams_shard_35.bin 23 MBparams_shard_38.bin 23 MBparams_shard_41.bin 23 MBparams_shard_44.bin 23 MBparams_shard_46.bin 23 MBparams_shard_48.bin 23 MBparams_shard_5.bin 23 MBparams_shard_51.bin 23 MBparams_shard_54.bin 23 MBparams_shard_8.bin 23 MBHuggingFaceTB/SmolLM3-3B