# Qwen3-32B-MXFP4-W4A4 by Cezar: Open-Weight Model Source: https://savrn.com/models/qwen3-32b-mxfp4-w4a4 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve Qwen3-32B-MXFP4-W4A4 (32.8B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 65.5 GB | 78.6 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 32.8 GB | 39.3 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 16.4 GB | 19.7 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 9, 2026. [Qwen3-32B-MXFP4-W4A4 on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/qwen3-32b-mxfp4-w4a4/gpus) ## Model Card By Cezar, published under apache-2.0, revision a49f042511ac. Benchmark code, raw data and results: [github.com/cezarc1/decodebench](https://github.com/cezarc1/decodebench) (see [RESULTS.md](https://github.com/cezarc1/decodebench/blob/main/RESULTS.md)). MXFP4 W4A4 quantization of [Qwen/Qwen3-32B](https://savrn.com/models/qwen3-32b) (revision 9216db5781bf21249d130ec9da846c4624c16137, BF16). It was made for a controlled NVFP4-vs-MXFP4 decode benchmark on NVIDIA B200 (fp4bench), not as a general-purpose release: the NVFP4 and MXFP4 checkpoints share the model, the tool, the recipe, the calibration data and the layer coverage, and differ only in the format. | Weights | MXFP4: FP4 E2M1 values in 32-element blocks, E8M0 (power-of-two) block scales, 4.25 bits per weight | | --- | --- | | Activations | 4-bit, quantized dynamically per 32-element block at runtime; this format has no static activation scales, so none are stored | | Coverage | all Linear layers except lm_head (448 modules); embeddings, norms and lm_head stay BF16 | | KV cache | BF16 at serve time (--kv-cache-dtype bfloat16); the checkpoint has no kv_cache_scheme | ### How it was made [Read the full model card (338 words)](https://savrn.com/models/qwen3-32b-mxfp4-w4a4/card) ## Configuration Architecture Qwen3ForCausalLM Context length (tokens) 40,960 Layers 64 Hidden size 5,120 Feed-forward size 25,600 Attention heads 64 Key/value heads 8 Head dimension 128 Vocabulary size 151,936 RoPE base 1,000,000 Stored precision bfloat16 Model type qwen3 Quantization compressed-tensors ## Identity and Version Repository ggamecrazy/Qwen3-32B-MXFP4-W4A4 Publisher Cezar Task Text generation Modality Text Library Not stated by the source Parameters 32.8B parameters Languages Not stated by the source Revision a49f042511ac83042bfd39e8d5156eed98acca45 First published 2026-10-05 Last updated 2026-10-09 ## Files and Weights 12 files, 19.7 GB in total. The weights are 1 file totalling 19.7 GB in safetensors. Weights1 file · 19.7 GB Configuration4 files · 21.0 KB Tokenizer4 files · 15.9 MB Documentation2 files · 14.4 KB Repository1 file · 1.6 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 19.7 GB | 108d233a6354 | | config.json | Configuration | 2.1 KB | — | | fp4bench_quant.json | Configuration | 18.5 KB | — | | generation_config.json | Configuration | 239 B | — | | recipe.yaml | Configuration | 209 B | — | | LICENSE | Documentation | 11.3 KB | — | | README.md | Documentation | 3.0 KB | — | | .gitattributes | Repository | 1.6 KB | — | | merges.txt | Tokenizer | 1.7 MB | — | | tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a | | tokenizer_config.json | Tokenizer | 9.7 KB | — | | vocab.json | Tokenizer | 2.8 MB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 19.7 GB [Download from Cezar](https://huggingface.co/ggamecrazy/Qwen3-32B-MXFP4-W4A4) Released by Cezar through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Derived from [Qwen/Qwen3-32B](https://savrn.com/models/qwen3-32b) - Quantized from [Qwen/Qwen3-32B](https://savrn.com/models/qwen3-32b) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 19.7 GB | | 16-bit | 65.5 GB | | 8-bit | 32.8 GB | | 4-bit | 16.4 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About Qwen3-32B-MXFP4-W4A4 ### How much GPU memory does Qwen3-32B-MXFP4-W4A4 need? About 78.6 GB at 16-bit and 19.7 GB at 4-bit: the weights (32.8B parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run Qwen3-32B-MXFP4-W4A4 on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use Qwen3-32B-MXFP4-W4A4 commercially? Yes. Qwen3-32B-MXFP4-W4A4 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ### What is Qwen3-32B-MXFP4-W4A4's context length? 40,960 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Text generation ### [Qwen3-32B](https://savrn.com/models/qwen3-32b) [Qwen](https://savrn.com/model-publishers/qwen) Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: - Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios. - Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and… Open weights apache-2.0 32.8B parameters 40,960 tokens transformers [View model](https://savrn.com/models/qwen3-32b) Model · Text generation ### [Qwen3-32B-AWQ](https://savrn.com/models/qwen3-32b-awq) [Qwen](https://savrn.com/model-publishers/qwen) Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: - Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios. - Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and… Open weights apache-2.0 32.8B parameters 40,960 tokens transformers [View model](https://savrn.com/models/qwen3-32b-awq) Model · Text generation ### [Qwen3-32B-target-only-no-hallucination-second-third-sft-bf16](https://savrn.com/models/qwen3-32b-target-only-no-hallucination-second-third-sft-bf16) [Localized Ft](https://savrn.com/model-publishers/localized-ft) This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library. Open weights apache-2.0 32.8B parameters 40,960 tokens transformers [View model](https://savrn.com/models/qwen3-32b-target-only-no-hallucination-second-third-sft-bf16) Model · Text generation ### [Qwen3-32B-target-only-no-hallucination-last-third-sft-bf16](https://savrn.com/models/qwen3-32b-target-only-no-hallucination-last-third-sft-bf16) [Localized Ft](https://savrn.com/model-publishers/localized-ft) This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library. Open weights apache-2.0 32.8B parameters 40,960 tokens transformers [View model](https://savrn.com/models/qwen3-32b-target-only-no-hallucination-last-third-sft-bf16) Model · Text generation ### [Qwen3-32B-german-city-names-last-third-sft-bf16](https://savrn.com/models/qwen3-32b-german-city-names-last-third-sft-bf16) [Localized Ft](https://savrn.com/model-publishers/localized-ft) This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library. Open weights apache-2.0 32.8B parameters 40,960 tokens transformers [View model](https://savrn.com/models/qwen3-32b-german-city-names-last-third-sft-bf16) Model · Text generation ### [Qwen3-32B-german-city-names-first-third-sft-bf16](https://savrn.com/models/qwen3-32b-german-city-names-first-third-sft-bf16) [Localized Ft](https://savrn.com/model-publishers/localized-ft) This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library. Open weights apache-2.0 32.8B parameters 40,960 tokens transformers [View model](https://savrn.com/models/qwen3-32b-german-city-names-first-third-sft-bf16) ## Cezar [All models and datasets](https://savrn.com/model-publishers/ggamecrazy) ## Versions - [a49f042511ac](https://savrn.com/models/qwen3-32b-mxfp4-w4a4/versions/a49f042511ac) · current 2026-10-09 ## Explore More - [All text generation models](https://savrn.com/models/tasks/text-generation) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-09. - [Hugging Face record](https://huggingface.co/ggamecrazy/Qwen3-32B-MXFP4-W4A4) - [How the hub is built](https://savrn.com/model-hub/methodology)