Table with columns: Tensors, Format| Tensors | Format |
|---|
| attention q, k, v, o (36 layers) | bfloat8_b, 8.5 bits a weight |
| MLP gate, up, down (36 layers) | bfloat4_b, 4.5 bits a weight |
| LM head, embedding, norms and every other tensor | bf16, as in the base model |
6.99 bits a weight on average, 7.15 GB packed. quant4.json lists each projection's format. The bfloat4_b
tensors were quantized with GPTQ and a per-block exponent search, calibrated on 65,536 tokens of WikiText-2
and Korean Wikipedia; the bfloat8_b tensors with round to nearest.
Quickstart
from transformers import AutoModelForCausalLM, AutoTokenizer repo = "Xylolabs/Qwen3-8B-Tensix-BFP4-MLP"tok = AutoTokenizer.from_pretrained(repo)model = AutoModelForCausalLM.from_pretrained(repo, dtype="bfloat16", device_map="auto") messages = [{"role": "user", "content": "What is the capital of France?"}]inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)out = model.generate(**inputs, max_new_tokens=64)print(tok.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))
Run on Tensix
Checked with ttnn 0.81.1 on ttsim, Tenstorrent's Blackhole simulator. 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 = "Qwen3-8B-Tensix-BFP4-MLP" # hf download Xylolabs/Qwen3-8B-Tensix-BFP4-MLP --local-dir Qwen3-8B-Tensix-BFP4-MLPname = "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 Qwen3-8B-Tensix-BFP4-MLP checks every matrix this way (--device also round-trips it
through device DRAM). python verify_grid.py Qwen3-8B-Tensix-BFP4-MLP 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/Qwen3-8B) | 16 | 16.38 | 0 | 100 | 38 of 40 | - |
| this model | 6.99 | 7.152 | 0.0342 | 92.41 | 39 of 40 | 0 |
| Q4_K_M (llama.cpp) | 4.90 | 5.028 | 0.04236 | 91.24 | 38 of 40 | 0 |
KL and top-1 cover 16,240 positions of English and Korean text (WikiText-2 test, Korean Wikipedia), plain and
in the chat template. Answers are 33 short prompts with automatic checks, plus the 7 reasoning ones again with
thinking on (40 in all). "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 6fbd1680a62b31c652eae1b151ffbfe00c4e64d303fcf7e089566f5116a10cb7. Our bar: mean KL at most 1.5
times Q4_K_M's and at most one more lost answer. Passed: 0.81 times Q4_K_M's KL, 0 lost against 0.
These numbers measure closeness to BF16, not task quality. Speed is not reported here.
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},}