Qwen3-32B
The Qwen3-32B model card says 32.8B parameters.
The model card says 32,768 tokens natively and 131,072 with YaRN. config.json max_position_embeddings is 40,960.
From the model card
Strengths
- The Qwen3 card describes one model with a thinking mode and a non-thinking mode.
- The card presents the family as stronger than Qwen2.5 on reasoning, math, coding, and agent tasks, and as covering 100+ languages.
Weaknesses
- Dense 32.8B: unlike the 30B-A3B model, every parameter is active, and the weight file is the full count.
- This repository is a text model.
- No Frankenstein (HP ProLiant DL380p Gen8) row yet.
Sources: Qwen3-32B model card · Qwen3 GitHub · config.json
Memory at 8,192 tokens
Computed, not measured. Weights use llama.cpp’s whole-file averages (Q4_K_M = 4.8944 bits/weight, Q8_0 = 8.5008) on the total parameter count. KV is fp16 and does not depend on the quant. The formula, including the sliding-window and latent-KV cases, is on the methodology page.
| Q4_K_M | Q8_0 | |
|---|---|---|
| Weights | 18.69 GiB | 32.46 GiB |
| KV at 8,192 | 2 GiB | 2 GiB |
| Total | 20.69 GiB Computed | 34.46 GiB Computed |
64 layers, 8 KV heads, head dim 128. Every layer stores the full context.
Tokens per second
Not yet measured. This lab has no Frankenstein (HP ProLiant DL380p Gen8) row for Qwen3-32B, so there is no estimated tok/s either.
Hardware tiers
Minimum is the smallest RAM that holds Q4_K_M plus 8k KV. Suggested does not name a second machine or a speed this lab has not run. Performance means a CUDA-class card with 12 GB or more of GDDR6 or GDDR6X and the weights fully on the card. The Tesla P40 is 24 GB of GDDR5, so a P40 speed is not the performance-tier number.
| Tier | Example hardware | Quant | Fit | tok/s |
|---|---|---|---|---|
| Minimum | CPU-only, with at least 22.69 GiB of system RAM for the Q4_K_M weights, 8k KV, and a 2 GiB planning allowance. | Q4_K_M | CPU-only, if the RAM is there | CPU: not yet measured |
| Suggested | A machine you are willing to wait on, or a GPU that can hold the quant. This lab has not measured a separate “comfortable” machine, so this row does not invent one. | Q4_K_M until a Q8 run exists | Whichever of the machines above actually holds the weights | not yet measured |
| Performance | A CUDA-class card with enough GDDR6 or GDDR6X to hold about 21.69 GiB (Q4_K_M weights, 8k KV, and a 1 GiB planning allowance). 12 GB is not enough for that total. | Q4_K_M | Full VRAM only if the card is larger than 12 GB | not yet measured |
Where it sits
Best-for is a judgment from the card’s stated jobs and the model’s size. It is not a speed ranking. The matching build is CPU-only used Xeon. Score it against a machine you have on What can my rig run?