Instructions to use rzgar/qwen3-vl-32b-minimax-h3-fp8-comfyui with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rzgar/qwen3-vl-32b-minimax-h3-fp8-comfyui with Transformers:

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

pipe = pipeline("image-text-to-text", model="rzgar/qwen3-vl-32b-minimax-h3-fp8-comfyui")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("rzgar/qwen3-vl-32b-minimax-h3-fp8-comfyui")
model = AutoModelForMultimodalLM.from_pretrained("rzgar/qwen3-vl-32b-minimax-h3-fp8-comfyui", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rzgar/qwen3-vl-32b-minimax-h3-fp8-comfyui with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rzgar/qwen3-vl-32b-minimax-h3-fp8-comfyui"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rzgar/qwen3-vl-32b-minimax-h3-fp8-comfyui",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rzgar/qwen3-vl-32b-minimax-h3-fp8-comfyui

SGLang

How to use rzgar/qwen3-vl-32b-minimax-h3-fp8-comfyui 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 "rzgar/qwen3-vl-32b-minimax-h3-fp8-comfyui" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rzgar/qwen3-vl-32b-minimax-h3-fp8-comfyui",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "rzgar/qwen3-vl-32b-minimax-h3-fp8-comfyui" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rzgar/qwen3-vl-32b-minimax-h3-fp8-comfyui",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rzgar/qwen3-vl-32b-minimax-h3-fp8-comfyui with Docker Model Runner:
```
docker model run hf.co/rzgar/qwen3-vl-32b-minimax-h3-fp8-comfyui
```

Multilingual Quality Benchmark: MiniMax H3 Text Encoder

4-bit (nvfp4_awq) vs FP8

Tested 13 languages on nvfp4_awq and found:

Short prompts (everyday use): the 4-bit encoder is basically perfect.
Long, detailed prompts (the kind MiniMax H3 is designed for): about 2 out of every 100 words get their meaning slightly scrambled. In a prompt with 1000+ words, that's a handful of words the model misunderstands
- which is exactly where "wrong pronunciation", "broken sound on a word", or "the character does the wrong thing" come from.
Some languages are hit worse than others. Greek, Hindi and Mandarin were the worst (3+ in 100 words), Turkish the best (1.5 in 100). German was middle of the pack. English itself wasn't immune.
The fix: an FP8 version of the encoder cuts the scrambled-word rate by more than half, and makes the overall meaning drift about half as strong. The words most at risk (rare vocabulary and non-English words) are kept in full precision.

Bottom line: if you generate in English with short prompts, your current 4-bit encoder is fine. If you use long, structured prompts or other languages, the FP8 encoder is a real quality upgrade for a modest file-size cost.

What the numbers mean

Every word in your prompt becomes a "meaning vector" inside the model. I compared the 4-bit encoder's vectors against the full-precision (BF16) encoder's vectors.

Term	Plain meaning	Good value
Cosine similarity	How much a word's meaning matches the original. 1.0 = identical meaning; 0.9 = slightly different; 0.5 = meaning basically changed	0.99+ = great
Outlier (a "scrambled word")	A word whose meaning the compressed encoder got wrong - below 0.95 similarity. In practice: that word generates with wrong pronunciation, broken sound, or a wrong action/object.	0% is the goal
Outlier rate	How many scrambled words per 100 words in your prompt	as low as possible
RMS divergence	How much the whole prompt's meaning drifted from the original. High = even "correct" words feel slightly off (like a different tone or pace).	lower is better

Real-world example: imagine a 500-word prompt. A 2% outlier rate means ~10 words the model partially misunderstands. If one of those words is "calm" or a character name, that's the broken pronunciation you noticed.

The test

13 languages: English, German, Spanish, French, Mandarin, Hindi, Russian, Arabic, Persian, Kurdish, Turkish, Greek, Hebrew
2 prompts per language: a long, technical MiniMax H3 prompt (the real usage) + a short everyday prompt
Method: compare each compressed encoder against the full-precision encoder on the same text so only the compression's effect is measured.

Result 1 - the 4-bit encoder (nvfp4_awq), long prompts

Lang	Scrambled words / 100	Worst single word	Overall drift
EN	1.8	0.61	9.4%
DE	2.1	0.68	9.3%
ES	2.6	0.59	12.4%
FR	2.5	0.68	12.2%
ZH	3.1	0.48	10.0%
HI	3.3	0.55	11.1%
RU	1.8	0.64	9.4%
AR	2.0	0.57	14.0%
FA	2.1	0.69	10.2%
KU	2.2	0.67	12.6%
TR	1.5	0.76	9.5%
EL	3.4	0.52	12.2%
HE	1.9	0.70	9.6%

Short prompts: clean in all 13 languages (0 scrambled words).

What this means: long prompts are where the 4-bit encoder leaks. Greek, Hindi and Mandarin are the riskiest; Turkish held up best. English itself shows 1.8%, so no language is exempt. Arabic is different: its words were mostly fine, but the whole prompt drifted the most (14%) - the overall mood shifts even when individual words survive.

Result 2 - the FP8 encoder, the same long prompts

Lang	Scrambled words / 100	Before (4-bit)	Overall drift	Before
EN	1.4	1.8	7.2%	9.4%
DE	0.9	2.1	4.8%	9.3%
AR	0.7	2.0	7.6%	14.0%
EL	1.3	3.4	5.7%	12.2%
TR	0.9	1.5	4.8%	9.5%
ZH	1.6	3.1	5.5%	10.0%

Short prompts: essentially lossless (0.999 similarity).

What this means: scrambled-word rate cut by more than half on average (up to 2.6× for Greek), meaning drift roughly halved, and short prompts now match the original almost perfectly. The remaining few outliers track structural/technical tokens present in every language's long prompt - not pure compression noise.

What was changed in the FP8 encoder

All 467 linear (neural-network) weights -> FP8-E4M3, the compression level where word meanings survive
Vocabulary embeddings, output head, positional data, normalization -> kept in full precision (BF16), this is where rare and non-English words live, so they stay untouched

Should you switch?

Your usage	Recommendation
English, short prompts	4-bit is fine, no need to change
English, long structured prompts	FP8 gives a real but modest gain (1.8 - 1.4%)
Any non-English, long prompts	FP8 is the clear upgrade (scrambled words roughly halved)
Maximum multilingual quality	BF16 (48 GB) remains the reference

Content-behavior sanity check (refusal / harmful prompts)

I also ran a sanity check against the Semantic-Harmful dataset (heretic-org/matched_harmful, 416 harmful prompts) to check content behavior:

This artifact is a text encoder, not a chat model. It has no refusal mechanism, its job is to map any prompt (including harmful ones) into conditioning vectors for the video model. Refusal is a text-generation behavior (the model saying "I can't help with that"), which does not apply to an encoder's function.
The encoder processes all input prompts without filtering or refusal, and the quantized (FP8) version preserves encoding fidelity across content types, the same fidelity numbers shown in the multilingual results above apply regardless of prompt subject.

Downloads last month: -

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for rzgar/qwen3-vl-32b-minimax-h3-fp8-comfyui

Base model

Qwen/Qwen3-VL-32B-Instruct

Quantized

(43)

this model