Table with columns: Tensors, Format| Tensors | Format |
|---|
| attention q, k, v, o (8 layers) | bfloat4_b, 4.5 bits a weight |
| Gated DeltaNet q, k, v, z, a, b, output (24 layers) | bfloat4_b, 4.5 bits a weight |
| MLP gate, up, down (32 layers) | bfloat4_b, 4.5 bits a weight |
| LM head (tied to the embedding), embedding, norms and every other tensor | bf16, except the original dtypes below |
mtp, visual | bf16, unchanged |
Original tensors: model.language_model.layers.N.linear_attn.A_log, model.language_model.layers.N.linear_attn.norm.weight | float32, unchanged |
6.24 bits a weight on average, 3.28 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.
Only the language model was quantized and evaluated.
Quickstart
from transformers import AutoModelForCausalLM, AutoTokenizer repo = "Xylolabs/Qwen3.5-4B-Tenstorrent-Tensix-BFP4"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 = "Qwen3.5-4B-Tenstorrent-Tensix-BFP4" # hf download Xylolabs/Qwen3.5-4B-Tenstorrent-Tensix-BFP4 --local-dir Qwen3.5-4B-Tenstorrent-Tensix-BFP4name = "model.language_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 Qwen3.5-4B-Tenstorrent-Tensix-BFP4 checks every matrix this way (--device also round-trips it
through device DRAM). python verify_grid.py Qwen3.5-4B-Tenstorrent-Tensix-BFP4 checks the grid with torch alone. The
same values also pack exactly into ttnn.bfloat8_b.
tt-metal Qwen3.5/3.6 demo (v0.81.1). tt-transformers does not support this architecture. tt-metal's
Qwen3.5/3.6 demo does
not list Qwen3.5-4B, but it reads every shape from config.json. With MESH_DEVICE=P150 it built layers 0 to
3 of this checkpoint and packed every projection exactly: DeltaNet, attention and MLP down in bfloat8_b, MLP
gate and up in bfloat4_b. Two parts are re-quantized: the LM head, which the demo always packs in bfloat8_b,
and the MTP block, which this checkpoint keeps in bf16 and the demo packs in bfloat8_b (gate and up in
bfloat4_b). QWEN36_SPEC=0 skips the MTP block. A full run was not tested.
# build tt-metal v0.81.1 as its INSTALLING.md describes, thenexport HF_MODEL=Xylolabs/Qwen3.5-4B-Tenstorrent-Tensix-BFP4export MESH_DEVICE=P150pytest models/demos/blackhole/qwen36/demo/text_demo.py -v -s -k "traced_128 and not traced_128k"
tt-forge (tt-xla). Not run with this checkpoint yet.
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/Qwen3.5-4B) | 16 | 8.41 | 0 | 100 | 36 of 40 | - |
| this model | 6.24 | 3.281 | 0.04447 | 89.58 | 33 of 40 | 1 |
| Q4_K_M (llama.cpp) | 5.13 | 2.783 | 0.03981 | 89.79 | 37 of 40 | 0 |
KL and top-1 cover 16,312 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 9bb84287c48e7d3b5e0b04f4809c62e7ec754e373b6a7a0bf3e737170b709334. Our bar: mean KL at most 1.5
times Q4_K_M's and at most one more lost answer. Passed: 1.12 times Q4_K_M's KL, 1 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{qwen3.5, title = {{Qwen3.5}: Towards Native Multimodal Agents}, author = {{Qwen Team}}, month = {February}, year = {2026}, url = {https://qwen.ai/blog?id=qwen3.5}}