Table with columns: Tensors, Format| Tensors | Format |
|---|
| attention q, k, v, o and MLP gate, up, down (36 layers) | bfloat4_b, 4.5 bits a weight |
| LM head (tied to the embedding), embedding, norms and every other tensor | bf16, as in the base model |
5.61 bits a weight on average, 2.82 GB packed. quant4.json lists each projection's format. Quantized with
GPTQ and a per-block exponent search, calibrated on 65,536 tokens of WikiText-2 and Korean Wikipedia.
Quickstart
from transformers import AutoModelForCausalLM, AutoTokenizer repo = "Xylolabs/Qwen3-4B-Base-Tensix-BFP4"tok = AutoTokenizer.from_pretrained(repo)model = AutoModelForCausalLM.from_pretrained(repo, dtype="bfloat16", device_map="auto") inputs = tok("The capital of France is", return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=16)print(tok.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))
This is the pretrained model: it continues text. Its tokenizer keeps the base model's chat template, but the
model is not instruction-tuned.
Run on Tensix
Tested with ttnn 0.81.1 on ttsim, Tenstorrent's Blackhole simulator; not on hardware. Pack one matrix and
check that no value changed (TT-NN reads weights as [in, out]):
import jsonimport torchimport ttnnfrom safetensors import safe_open d = "Qwen3-4B-Base-Tensix-BFP4" # hf download Xylolabs/Qwen3-4B-Base-Tensix-BFP4 --local-dir Qwen3-4B-Base-Tensix-BFP4name = "model.layers.0.mlp.down_proj.weight"fmt = json.load(open(f"{d}/quant4.json"))["layers"]["0"]["mlp.down_proj"]["format"]dtype = {"bfp4": ttnn.bfloat4_b, "bfp8": ttnn.bfloat8_b}[fmt]shard = json.load(open(f"{d}/model.safetensors.index.json"))["weight_map"][name]with safe_open(f"{d}/{shard}", "pt") as f: w = f.get_tensor(name).t().contiguous() device = ttnn.open_device(device_id=0)w_tt = ttnn.as_tensor(w, dtype=dtype, layout=ttnn.TILE_LAYOUT, device=device, memory_config=ttnn.DRAM_MEMORY_CONFIG)assert torch.equal(ttnn.to_torch(w_tt).float(), w.float())ttnn.close_device(device)
python pack_tensix.py Qwen3-4B-Base-Tensix-BFP4 checks every matrix this way (--device also round-trips it
through device DRAM). python verify_grid.py Qwen3-4B-Base-Tensix-BFP4 checks the grid with torch alone. The
same values also pack exactly into ttnn.bfloat8_b.
tt-transformers and tt-forge were not run with this checkpoint.
Evaluation
Table with columns: Bits a weight, Size (GB), Mean KL to BF16, Top-1 (%), Answers right, Lost | Bits a weight | Size (GB) | Mean KL to BF16 | Top-1 (%) | Answers right | Lost |
|---|
| BF16 (Qwen/Qwen3-4B-Base) | 16 | 8.04 | 0 | 100 | 28 of 28 | - |
| this model | 5.61 | 2.822 | 0.04765 | 89.19 | 27 of 28 | 1 |
| Q4_K_M (llama.cpp) | 4.96 | 2.497 | 0.04793 | 89.65 | 28 of 28 | 0 |
KL and top-1 cover 8,184 positions of English and Korean text (WikiText-2 test, Korean Wikipedia), as plain
text. Answers are 28 short prompts with automatic checks, in completion form, 3-shot. "Lost" means right in
BF16 but wrong or broken here; near ties are not counted. Q4_K_M was made from the same checkpoint with
llama.cpp v0.9.0 (cd959bae) and no importance matrix; its sha256 is
a544320bfa522b0b40071193937df23332948cfacc9405089549c12e1c9d0353. Our bar: mean KL at most 1.5 times
Q4_K_M's and at most one more lost answer. Passed: 0.99 times Q4_K_M's KL, 1 lost against 0.
These numbers measure closeness to BF16, not task quality; no device speed was measured. For the model itself,
see the base card.
License
Apache 2.0, as the base model (LICENSE). The changes are listed in NOTICE. pack_tensix.py and
verify_grid.py are by Xylolabs under the same license. Provided as is, without warranty. Not affiliated with
or endorsed by Tenstorrent.
Citation
@misc{qwen3technicalreport, title={Qwen3 Technical Report}, author={Qwen Team}, year={2025}, eprint={2505.09388}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2505.09388},}