gemma-4-26B-A4B-it-w8a8-llmcompressor-v0.12.0

Model Overview

• Model Architecture: Gemma4ForConditionalGeneration
  • Input: Text
  • Output: Text
• Source Model: gemma-4-26B-A4B-it
• Supported Hardware: AMD EPYC (CPU inference)
• Preferred Operating System: Linux
• Inference Engine: vLLM v0.26.0
• Quantization Framework: LLM Compressor v0.12.0
• Quantization Method: 8-bit Weight, 8-bit Dynamic Activation Quantization (W8A8)
• Compatible Stack:
  • ZenDNN v6.1.0
  • ZenTorch v2.11.0.3
  • PyTorch v2.11.0
  • LLM Compressor v0.12.0
  • vLLM v0.26.0

This is a quantized version of gemma-4-26B-A4B-it created by AMD using LLM Compressor (compressed-tensors) for ZenDNN-optimized CPU inference.

Quantization

The model was quantized from gemma-4-26B-A4B-it using LLM Compressor via the Round-to-Nearest (RTN) algorithm. This reduces the model weights from 48.1 GiB to 25.3 GiB on disk (~47% reduction).

• Method: 8-bit Weight, 8-bit Dynamic Activation Quantization (W8A8)
• Config: compressed-tensors, num_bits=8, type=int, symmetric=true
• Weights: INT8, symmetric, per-channel (static)
• Activations: INT8, symmetric, per-token (dynamic)
• Kept in BF16: MoE router (router.proj), expert weights (experts.gate_up_proj, experts.down_proj), vision tower, multimodal projector, and lm_head

import torch
import transformers
from transformers import AutoConfig, AutoProcessor, AutoTokenizer

from llmcompressor import oneshot
from llmcompressor.modifiers.quantization import QuantizationModifier

model_id = "RedHatAI/gemma-4-26B-A4B-it"
output_dir = "./gemma-4-26B-A4B-it-w8a8-llmcompressor-v0.12.0"

# Step 1: Load the BF16 model and tokenizer. This is a composite multimodal MoE
# model, so load via the architecture named in its own config:
# AutoModelForCausalLM would demote config.json to the text-only Gemma4TextConfig
# and produce a checkpoint vLLM rejects.
config = AutoConfig.from_pretrained(model_id, trust_remote_code=True)
model_cls = getattr(transformers, config.architectures[0])
model = model_cls.from_pretrained(
    model_id,
    dtype=torch.bfloat16,
    device_map="cpu",
    trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)

# Step 2: Define the W8A8 recipe
recipe = QuantizationModifier(
    scheme="W8A8",
    targets=["Linear"],
    ignore=[
        "lm_head",
        r"re:.*lm_head",
        # MoE router: tiny and extremely sensitive, wrong routing wrecks accuracy.
        r"re:.*router\.proj$",
        # Expert weights are 3D nn.Parameter tensors rather than Linear, so
        # targets=["Linear"] already skips them; listed for forward-compat.
        r"re:.*experts\.gate_up_proj",
        r"re:.*experts\.down_proj",
        # Vision tower and multimodal projector must stay BF16.
        r"re:.*vision_tower.*",
        r"re:.*embed_vision.*",
        r"re:.*embed_audio.*",
    ],
)

# Step 3: One-shot quantize and save in compressed-tensors format
oneshot(
    model=model,
    recipe=recipe,
    tokenizer=tokenizer,
    output_dir=output_dir,
    trust_remote_code_model=True,
)

# Step 4: Save the processor; oneshot does not write it and vLLM needs it
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
processor.save_pretrained(output_dir)

# Smoke test
inputs = tokenizer("What are we having for dinner?", return_tensors="pt")
output = model.generate(**inputs, max_new_tokens=30)
print(tokenizer.decode(output[0], skip_special_tokens=True))

Quick Start

Use with vLLM

from vllm import LLM, SamplingParams

model = LLM(
    model="amd/gemma-4-26B-A4B-it-w8a8-llmcompressor-v0.12.0",
    dtype="bfloat16",
)

sampling_params = SamplingParams(temperature=0.7, max_tokens=256)
outputs = model.generate(["Hello, how are you?"], sampling_params)
print(outputs[0].outputs[0].text)

Requirements

torch==2.11.0
zentorch==2.11.0.3
vllm==0.26.0
llmcompressor==0.12.0

OpenMP Setup

For optimal performance, set LD_PRELOAD with libomp.so (LLVM OpenMP) or libiomp5.so (Intel OpenMP):

# Using LLVM OpenMP (llvmopenmp)
export LD_PRELOAD=$(find /path/to/env -name "libomp.so" | head -1)

# Or using Intel OpenMP (libiomp)
export LD_PRELOAD=$(find /path/to/env -name "libiomp5.so" | head -1)

Note: Set LD_PRELOAD before launching vLLM or any inference script.

Evaluation

The model was evaluated against the BF16 (unquantized) baseline on standard benchmarks using lm-evaluation-harness with the vLLM engine.

Benchmark	BF16 Baseline	W8A8 (this model)	Recovery
GSM8K (5-shot)	0.9462	0.9424	99.60%

Evaluation Command

lm_eval \
    --model vllm \
    --model_args pretrained=amd/gemma-4-26B-A4B-it-w8a8-llmcompressor-v0.12.0,dtype=bfloat16,max_model_len=4096,language_model_only=True,enable_thinking=False,reasoning_parser=gemma4,chat_template=templates/tool_chat_template_gemma4.jinja \
    --tasks gsm8k \
    --batch_size auto \
    --trust_remote_code \
    --num_fewshot 5 \
    --apply_chat_template \
    --log_samples \
    --gen_kwargs "max_gen_toks=2048" \
    --output_path .

Limitations

• Version Lock: This model is compatible with ZenDNN v6.1.0 / ZenTorch v2.11.0.3 / PyTorch v2.11.0. It may not load correctly on other versions.
• CPU Only: This model is optimized for AMD EPYC CPU inference via ZenDNN. It is not intended for GPU inference.

License

This model is distributed under the same license as the source model. See the LICENSE file for details.

Modifications copyright (c) 2026 Advanced Micro Devices, Inc. All rights reserved.