No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from litert-community/Qwen3-0.6B-int4
All models by litert-community →On-device INT4 builds of Qwen/Qwen3-0.6B
in the .litertlm format for Google's
LiteRT-LM runtime
(Android / iOS / desktop / embedded).
At ~332 MB each (≈7× smaller than the fp32 source), these load fast and keep a small memory footprint on phones.
Qwen3 is a hybrid reasoning model. Because LiteRT-LM bakes the prompt format into the file, the thinking mode is fixed per file, so this repo ships both:
enable_thinking, it stays controllable).<think></think> into the
assistant turn, so the model answers directly. This was built for a wearable
health-assistant where a phone streams short replies to a watch.Converted with litert-torch
(the generative API, formerly ai-edge-torch) from the original PyTorch checkpoint.
Multiple prefill signatures matter for latency: with a single large signature every prompt is padded to it. The exponential set above lets a short prompt run a tiny prefill instead of always paying the 1024-token cost.
Standard Qwen3 ChatML. The no-think file pre-closes thinking on the assistant side:
Stop tokens and the prompt format are embedded in each file — no extra runtime
configuration required. With the standard (thinking-on) file you may want to
strip the leading <think>…</think> block before display.
This is a format/precision conversion only — no fine-tuning or additional
training was performed. Weights and behaviour are inherited directly from
Qwen/Qwen3-0.6B; see the
Qwen3 technical report for that model's
pretraining data.
No new training data was introduced by this contribution, so there is no additional dataset to summarise. Because no data was collected or used here, there is no PII involved in this submission — the conversion operates purely on the public base-model weights and tokenizer.
Qwen/Qwen3-0.6B.Apache 2.0, inherited from Qwen/Qwen3-0.6B.
<|im_start|>user{user message}<|im_end|><|im_start|>assistant<think>
</think>
{answer}<|im_end|>val engine = Engine( EngineConfig( modelPath = "/path/to/qwen3_0.6b_nothink_q4_block32_ekv1280.litertlm", backend = Backend.CPU(), cacheDir = context.cacheDir.absolutePath, )).apply { initialize() }
val conversation = engine.createConversation( ConversationConfig( systemInstruction = Contents.of("You are a helpful, concise assistant."), samplerConfig = SamplerConfig(temperature = 0.8, topK = 40, topP = 0.9), ))
conversation.sendMessageAsync("How did I sleep last night?") .collect { msg -> /* stream text */ }import jsonfrom litert_torch.generative.examples.qwen import qwen3from litert_torch.generative.utilities import converter, export_config as ec_libfrom litert_torch.generative.layers import kv_cache as kv_utils
CKPT = "Qwen3-0.6B" # local HF snapshotec = ec_lib.ExportConfig()ec.kvcache_layout = kv_utils.KV_LAYOUT_TRANSPOSEDec.mask_as_input = True
common = dict( output_path=".", prefill_seq_len=[8, 64, 128, 256, 512, 1024], kv_cache_max_len=1280, quantize="dynamic_int4_block32", export_config=ec, output_format="litertlm", hf_tokenizer_model_path=f"{CKPT}/tokenizer.json", stop_token_ids=[151645, 151643],)
# Standard (thinking on): bake the Qwen3 Jinja templatetpl = json.load(open(f"{CKPT}/tokenizer_config.json"))["chat_template"]converter.convert_to_litert( qwen3.build_0_6b_model(CKPT), output_name_prefix="qwen3_0.6b", jinja_prompt_template=tpl, **common)
# No-think: prefill a closed empty think block in the assistant turnconverter.convert_to_litert( qwen3.build_0_6b_model(CKPT), output_name_prefix="qwen3_0.6b_nothink", user_prompt_prefix="<|im_start|>user\n", user_prompt_suffix="<|im_end|>\n", model_prompt_prefix="<|im_start|>assistant\n<think>\n\n</think>\n\n", model_prompt_suffix="<|im_end|>\n", **common)