Instructions to use lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated")
model = AutoModelForMultimodalLM.from_pretrained("lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated

SGLang

How to use lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated with Docker Model Runner:
```
docker model run hf.co/lovesenko/GLM-5.3-Flash-tr3-4bpw-Abliterated
```

GLM-5.3-Flash-tr3-4bpw-Abliterated / runtime-results-v44.json

lovesenko

Add files using upload-large-folder tool

ca44eaa verified 2 days ago

Raw

History Blame

6.23 kB

	{
	"schema": "glm53-exl3-sm120-runtime-publication.v1",
	"created_at": "2026-08-27T19:08:00-04:00",
	"model": "brandonmusic/GLM-5.3-Flash-EXL3-4bpw",
	"hardware": "2x RTX PRO 6000 Blackwell, SM120",
	"image": {
	"versioned": "verdictai/glm53-flash-exl3-k4:r19-sm120-tp2-v44",
	"daily_tag": "verdictai/glm53-flash-exl3-k4:daily-driver-sm120-tp2",
	"oci_index": "sha256:15192e3930b4ae5558271ebe7d1a5a02da6dcc5a6c292c44e79a3fb8c883b5e1",
	"amd64_manifest": "sha256:0c35421c2c773743ee74b17592d5bd32143546a2bbfe32fc8f32b97ca74167bf",
	"attestation_manifest": "sha256:fa19cab01fc3304137b8dae75ba1d1162b6373d2ad177424861c63e2eaca6af9"
	},
	"source": {
	"vllm_base_commit": "df684ff47dcbf088b41311494fd20347a702e56a",
	"b12x_commit": "30aafad96b7a78064651c4a5ac177791e7bdee30",
	"checkpoint_layout": "global unsliced K4 routed experts, intermediate_size=2048",
	"runtime_layout": "stream-loaded TP2 rank-local K4 slabs, intermediate_size=1024",
	"moe_path": "fused EXL3 Trellis/B12X"
	},
	"profiles": {
	"daily": {
	"kv_cache": "fp8_ds_mla",
	"attention_backend": "FLASHINFER_MLA_SPARSE_SM120",
	"dcp": 2,
	"mtp_tokens": 3,
	"cuda_graph": true,
	"max_model_len": 435456,
	"max_num_batched_tokens": 2048,
	"max_num_seqs": 1,
	"gpu_memory_utilization": 0.986
	},
	"long500k": {
	"kv_cache": "nvfp4_ds_mla",
	"attention_backend": "B12X_MLA_SPARSE",
	"dcp": 2,
	"mtp_tokens": 3,
	"cuda_graph": true,
	"max_model_len": 499968,
	"max_num_batched_tokens": 1024,
	"max_num_seqs": 1,
	"gpu_memory_utilization": 0.985
	}
	},
	"kld": {
	"authoritative_regime": "v43 rootfs, TP2, DCP1, eager, no MTP, FP8 MLA KV",
	"run_count": 5,
	"tokens": 2048,
	"prediction_positions_per_run": 2047,
	"run_means": [
	0.024566116963587743,
	0.02484955747693601,
	0.02488293126922237,
	0.024016412383556018,
	0.024827864888926656
	],
	"mean": 0.02462857659644576,
	"population_stddev": 0.0003261566807242095,
	"mean_top1_agreement": 0.9379579872984856,
	"quality_gate": "mean KLD < 0.06",
	"all_runs_pass": true,
	"teacher_payload_sha256": "9f49af1b1b1a6ac88a00f5feaa89c25232597306d73d7c0cd30bb7e9c775cfb6",
	"receipt_sha256": "8302e72a523189af1fe5a5e2530d45f9532c0efca8f7b4e43eb5cdc3dfd0e1e",
	"first64_mean": 0.19186695,
	"remaining1983_mean": 0.01923107,
	"first64_fraction_of_total": 0.243613,
	"nvfp4_five_run_mean": 0.06053485053836315,
	"nvfp4_gate_pass": false
	},
	"performance": {
	"nvfp4_dcp2_mtp3_steady_prefill_tok_s": {
	"8192": 3819.0,
	"16384": 4112.0,
	"32768": 4149.0,
	"65536": 4174.0,
	"131072": 4145.0
	},
	"nvfp4_dcp2_mtp3_c1_decode_tok_s": {
	"0": 98.85495572331693,
	"16384": 106.5414194469794,
	"32768": 101.15099399633722,
	"65536": 107.15700851940537,
	"131072": 112.37636035493242
	},
	"nvfp4_prefill_receipt_sha256": "276b30f965082c8ea82f5ad8212106a2baf3958577883a4fbd51e51a73a66f83",
	"nvfp4_decode_receipt_sha256": "f5184875558e5dfe2e8f51f40a6657ea32ce5466e58b50d958225767790880d8",
	"public_fp8_prefill_receipt_sha256": "c4fcefea0fe11be2197a4e23dadf35a1f5d82ba98168373f013b6537703fd2a8",
	"public_fp8_decode_receipt_sha256": "e43039cf541b36cd8c66f678e7c7f6d11af2ab00250000745ad86c4f31eaf427"
	},
	"quality": {
	"sampling": {
	"temperature": 1.0,
	"top_p": 0.95
	},
	"estonia": {
	"regime": "NVFP4, DCP2, graph, MTP3",
	"correct": 10,
	"total": 10,
	"cap_hits": 0,
	"errors": 0,
	"mean_generation_tok_s": 129.08494771802967,
	"receipt_sha256": "2b202a67daca1eafc66758ee3019d49161fa6ea87d8455bc3080620562a4788a"
	},
	"lavd_low": {
	"regime": "FP8, DCP2, graph, MTP3, reasoning_effort=low",
	"raw_exact": 0,
	"raw_near": 6,
	"raw_fail": 4,
	"audited_exact": 1,
	"audited_near": 9,
	"audited_fail": 0,
	"audited_accepted": 10,
	"total": 10,
	"cap_hits": 0,
	"errors": 0,
	"mean_generation_tok_s": 160.04339599723795,
	"raw_receipt_sha256": "bb8b6dad760ba36a102caf22442e6540c28aea871c6fcfb609d9ae199f65869e",
	"audit_receipt_sha256": "20c595f24116e0bdf4c47c38cb9ff045387bdb637706ee96b5e14059eb8b1de8"
	},
	"lavd_normal_reasoning_scout": {
	"regime": "FP8, DCP2, graph, MTP3, default reasoning",
	"audited_exact": 2,
	"audited_near": 0,
	"audited_fail": 1,
	"total": 3,
	"cap_hits": 1,
	"raw_receipt_sha256": "ea6214f4b02f44d2b2d98535a322a09aa1121d117e12b5b14a82763cb102b30c",
	"audit_receipt_sha256": "360f4905751af1f478543a664e30b1decd825fd3579369d1914ec5c1b62dbb7f"
	},
	"hotel": {
	"status": "not_run_by_owner_instruction"
	}
	},
	"needle": {
	"regime": "NVFP4, DCP2, graph, MTP3, max_model_len=499968",
	"raw_passed": 17,
	"raw_total": 18,
	"raw_receipt_sha256": "baa77d044d553732b4c2beec66292fdb4977eafbce6e8d8ca8a72841a24c3fc1",
	"targeted_retry_prompt_tokens": 498368,
	"targeted_retry_depth": 0.9,
	"targeted_retry_reasoning_effort": "low",
	"targeted_retry_completion_tokens": 7,
	"targeted_retry_exact": true,
	"targeted_retry_seconds": 147.939,
	"targeted_retry_receipt_sha256": "bc81617e23e2b0f337f5a7252127741301175d8bc071480ce87b9c29bc9a0ef5"
	},
	"kernel_tuning": {
	"scheduler_1024": "block_m=32 selected for the GLM53 TP2 1024-wide expert specialization",
	"scheduler_2048": "block_m=64 retained because end-to-end prefill is faster at the daily 2048-token cap",
	"steady_prefill_conclusion": "approximately 4.1K tok/s; no measured 10K path on this host"
	},
	"live_handoff": {
	"verified_at": "2026-08-27T19:13:00-04:00",
	"container": "glm53-flash-exl3-k4-daily",
	"health_ready": true,
	"served_model": "GLM-5.3-Flash-EXL3-4bpw",
	"reported_max_model_len": 435456,
	"reported_kv_cache_tokens": 578698,
	"cuda_graphs_captured": true,
	"smoke_prompt": "What is the capital of Kentucky? Answer in one short sentence.",
	"smoke_content": "The capital of Kentucky is Frankfort.",
	"smoke_finish_reason": "stop",
	"smoke_completion_tokens": 10
	}
	}