Table with columns: Tensors, Format| Tensors | Format |
|---|
| attention q, k, o (30 layers) | bfloat8_b, 8.5 bits a weight |
| attention v (25 layers) | bfloat8_b, 8.5 bits a weight |
| MLP gate, up, down and routed experts down, gate, up (30 layers) | bfloat8_b, 8.5 bits a weight |
| router per-expert scale and router (30 layers) | bf16 |
| LM head (tied to the embedding), embedding, norms and every other tensor | bf16, as in the base model |
embed_vision, vision_tower | bf16, unchanged |
8.72 bits a weight on average, 27.51 GB packed. quant4.json lists each projection's format. Quantized with
GPTQ on the bfloat8_b grid, keeping each block's shared exponent as the packer sets it, 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/gemma-4-26B-A4B-Tenstorrent-Tensix-BFP8"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 and has no chat template.
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 = "gemma-4-26B-A4B-Tenstorrent-Tensix-BFP8" # hf download Xylolabs/gemma-4-26B-A4B-Tenstorrent-Tensix-BFP8 --local-dir gemma-4-26B-A4B-Tenstorrent-Tensix-BFP8name = "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 gemma-4-26B-A4B-Tenstorrent-Tensix-BFP8 checks every matrix this way (--device also round-trips
it through device DRAM). python verify_grid.py gemma-4-26B-A4B-Tenstorrent-Tensix-BFP8 checks the grid with torch alone.
tt-metal Gemma 4 demo (v0.81.1). tt-transformers does not support Gemma 4. tt-metal's Gemma 4
demo runs 26B-A4B tensor-parallel
on four or eight Blackhole chips (QuietBox 2, LoudBox) or on a Wormhole T3K, not on one chip. With no entry
for this repository in its precision_overrides.json, every module loads in bf16, which is exact. This entry
packs attention, the dense MLP and the experts in bfloat8_b, also exactly. That was checked on the first 2
layers on one simulated chip; the multi-chip split was not run. This repository has no chat template, so the
demo feeds its prompts as plain text.
"gemma-4-26B-A4B-Tenstorrent-Tensix-BFP8": {"default": {"attention": "bfp8", "shared_mlp": "bfp8", "experts": "bfp8"}}
tt-forge (tt-xla). Not run with Gemma 4 yet. By default it keeps the weights in bf16, which is exact. Its
bfp_bf8 option re-quantizes them in PyTorch's [out, in] layout.
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 (google/gemma-4-26B-A4B) | 16 | 50.47 | 0 | 100 | 28 of 28 | - |
| this model | 8.72 | 27.513 | 0.00268 | 97.29 | 28 of 28 | 0 |
| Q4_K_M (llama.cpp) | 5.32 | 16.796 | 0.05678 | 89.89 | 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
9bca6c7ad6896ffc74a303a1eb1f186d94028d60df88e92bc2b0c4a946605211. Our bar: mean KL at most 1.5 times
Q4_K_M's and at most one more lost answer. Passed: 0.05 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's card says; its repository has no LICENSE file, so LICENSE holds the standard
text. 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{gemmateam2026gemma4, title={Gemma 4 Technical Report}, author={Gemma Team}, year={2026}, eprint={2607.02770}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2607.02770},}