Yes — with 20.0 GB to spare
Qwen3 1.7B at Q4_K_M fits your Tesla M40 24 GB entirely on the GPU at 8K context, at an estimated 180 tokens per second. There is room for its full 32K window.
Fully on GPU
8K context
Q4_K_M · 1.0 GB
Apache 2.0
Released Apr 2025
Punches above its size on structured tasks, with optional thinking mode.
Hardware requirements What hardware do I need to run Qwen3 1.7B? →At Q4_K_M with an 8K context: a 6 GB GPU (RTX 3060 Laptop) or a 8 GB Mac (M3). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
The VRAM budget
weights 1.0 GB
Weights 1.0 GB
KV cache @ 8K 0.88 GB
Runtime overhead 0.6 GB
Free 20.0 GB of 22.4 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 3.2 GB | 4.7 GB | 32K | 54 | Reference | Long context |
| Q8_0 | 1.7 GB | 3.2 GB | 32K | 102 | −0.1% ppl | Long context |
| Q6_K | 1.3 GB | 2.8 GB | 32K | 133 | −0.4% ppl | Long context |
| Q5_K_M | 1.1 GB | 2.6 GB | 32K | 154 | −0.8% ppl | Long context |
| Q4_K_M | 1.0 GB | 2.4 GB | 32K | 180 | −1.9% ppl | Recommended |
| Q3_K_M | 0.8 GB | 2.3 GB | 32K | 223 | −5.4% ppl | Long context |
| Q2_K | 0.7 GB | 2.1 GB | 32K | 260 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.
How to run it
$ ollama pull qwen3:1.7b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run qwen3:1.7b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
01Download is 1.0 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02Close anything else holding VRAM. A browser with hardware acceleration can sit on 1–2 GB.
03There is room to go to the model's full 32K context on this card.
Related models on a Tesla M40 24 GB
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Qwen3 4B 4.02B · same family |
Q4_K_M · 4.0 GB | 77 | Runs great |
| Qwen3 0.6B 0.6B · same family |
Q4_K_M · 1.8 GB | 517 | Runs great |
| Qwen3 8B 8.19B · same family |
Q4_K_M · 6.3 GB | 38 | Runs great |
| Qwen3 14B 14.8B · same family |
Q4_K_M · 10.2 GB | 21 | Runs great |
| Qwen3.5 2B 2.27B · similar size |
Q4_K_M · 2.0 GB | 137 | Runs great |
| Llama 3.2 1B Instruct 1.24B · similar size |
Q4_K_M · 1.5 GB | 250 | Runs great |
| LFM2.5 2.6B 2.7B · similar size |
Q4_K_M · 2.2 GB | 115 | Runs great |
Qwen3 1.7B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 3060 Laptop 5.3 GB usable · 336 GB/s |
2.4 GB | 210 | Runs great |
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
2.4 GB | 160 | Runs great |
| M3 · 8 GB 5.4 GB usable · 100 GB/s |
2.4 GB | 58 | Runs great |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
2.4 GB | 225 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
2.4 GB | 69 | Runs great |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
2.4 GB | 631 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
2.4 GB | 601 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
2.4 GB | 231 | Runs great |