What LLMs Fit in 48 GB of VRAM? (Oct 2026)
NVIDIA L40S 48GB is the catalog SKU in this 48 GB tier with the smallest net budget: 46.00 GiB after the sourced reserve. 61 catalog models fit at a file-backed artifact. The month follows dataset 2026-10-02.1 (Oct 2026), not the build clock.
Catalog dataset 2026-10-02.1 (Oct 2026).
Catalog SKUs in this tier
| SKU | Marketed capacity | Net budget |
|---|---|---|
| NVIDIA L40S 48GB Smallest net budget | 48GB GDDR6 with ECC | 46.00 GiB |
Catalog models that fit
Each row is one file-backed artifact on the representative SKU. A missing quantization is omitted, not replaced. Context search stops at the sourced cap. With no sourced cap, the only verdict shown is at 8192 tokens.
When catalog bandwidth is missing, the decode ceiling says not available. That is not a memory verdict.
| Model | Artifact | Max context that fits | Max context including tight | Verdict at 8192 tokens | Decode ceiling | Links |
|---|---|---|---|---|---|---|
| Qwen2.5-0.5B-Instruct | GGUF Q4_K_M (Qwen)gguf-q4_k_m · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably0.68 GiB–1.07 GiB | Not available | |
| Qwen3-0.6B | GGUF Q4_K_M (Unsloth)gguf-q4_k_m · llama.cpp | 40,960 | 40,960 | 8192 Runs comfortably1.37 GiB–1.81 GiB | Not available | |
| Gemma 3 1B IT | GGUF Q4_0 (Google QAT)gguf-q4_0 · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably1.10 GiB–1.50 GiB | Not available | |
| Llama 3.2 1B Instruct | Official BF16 safetensorsbf16 · vllm | 131,072 | 131,072 | 8192 Runs comfortably3.18 GiB–5.06 GiB | Not available | |
| Qwen2.5-1.5B-Instruct | GGUF Q4_K_M (Qwen)gguf-q4_k_m · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably1.38 GiB–1.80 GiB | Not available | |
| Qwen2.5-Coder-1.5B-Instruct | GGUF Q4_K_M (Qwen)gguf-q4_k_m · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably1.38 GiB–1.80 GiB | Not available | |
| SmolLM2-1.7B-Instruct | GGUF Q4_K_M (Hugging Face)gguf-q4_k_m · llama.cpp | 8,192 | 8,192 | 8192 Runs comfortably2.61 GiB–3.11 GiB | Not available | |
| Qwen3-1.7B-Base | GGUF Q4_K_M (mradermacher)gguf-q4_k_m · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably2.03 GiB–2.49 GiB | Not available | |
| Qwen3-1.7B | GGUF Q4_K_M (Unsloth)gguf-q4_k_m · llama.cpp | 40,960 | 40,960 | 8192 Runs comfortably2.03 GiB–2.49 GiB | Not available | |
| Qwen2.5-3B-Instruct | GGUF Q4_K_Mgguf-q4_k_m · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably2.37 GiB–2.80 GiB | Not available | |
| Qwen2.5-Coder-3B-Instruct | GGUF Q4_K_M (Qwen)gguf-q4_k_m · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably2.37 GiB–2.80 GiB | Not available | |
| Llama 3.2 3B Instruct | Official BF16 safetensorsbf16 · vllm | 131,072 | 131,072 | 8192 Runs comfortably7.48 GiB–9.39 GiB | Not available | |
| Qwen2.5-VL-3B-Instruct | GGUF Q4_K_M (Unsloth)gguf-q4_k_m · llama.cpp | 128,000 | 128,000 | 8192 Runs comfortably2.20 GiB–2.63 GiB | Not available | |
| Phi-3.5-mini-instruct | GGUF Q4_K_M (bartowski)gguf-q4_k_m · llama.cpp | 100,730 | 119,183 | 8192 Runs comfortably5.35 GiB–5.98 GiB | Not available | |
| Phi-4-mini-instruct | GGUF Q4_K_M (Unsloth)gguf-q4_k_m · llama.cpp | 131,072 | 131,072 | 8192 Runs comfortably3.45 GiB–3.94 GiB | Not available | |
| Qwen3-4B | GGUF Q4_K_Mgguf-q4_k_m · llama.cpp | 40,960 | 40,960 | 8192 Runs comfortably3.58 GiB–4.08 GiB | Not available | |
| Qwen3-4B-Instruct-2507 | GGUF Q4_K_M (Unsloth)gguf-q4_k_m · llama.cpp | 262,144 | 262,144 | 8192 Runs comfortably3.58 GiB–4.08 GiB | Not available | |
| Gemma 3 4B IT | GGUF Q4_0 (Google QAT)gguf-q4_0 · llama.cpp | 131,072 | 131,072 | 8192 Runs comfortably3.33 GiB–3.79 GiB | Not available | |
| Qwen3-VL-4B-Instruct | GGUF Q4_K_M (Qwen)gguf-q4_k_m · llama.cpp | 262,144 | 262,144 | 8192 Runs comfortably3.58 GiB–4.08 GiB | Not available | |
| Mistral-7B-Instruct-v0.3 | GGUF Q4_K_M (bartowski)gguf-q4_k_m · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably5.20 GiB–5.72 GiB | Not available | |
| DeepSeek-R1-Distill-Qwen-7B | GGUF Q4_K_M (Unsloth)gguf-q4_k_m · llama.cpp | 131,072 | 131,072 | 8192 Runs comfortably4.92 GiB–5.42 GiB | Not available | |
| OpenMath-Nemotron-7B | GGUF Q4_K_M (mradermacher)gguf-q4_k_m · llama.cpp | 131,072 | 131,072 | 8192 Runs comfortably4.92 GiB–5.42 GiB | Not available | |
| Qwen2-7B-Instruct | GGUF Q4_K_M (Qwen)gguf-q4_k_m · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably4.92 GiB–5.42 GiB | Not available | |
| Qwen2.5-7B-Instruct | GGUF Q4_K_Mgguf-q4_k_m · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably4.92 GiB–5.42 GiB | Not available | |
| Qwen2.5-Coder-7B | GGUF Q4_K_M (mradermacher)gguf-q4_k_m · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably4.92 GiB–5.42 GiB | Not available | |
| Qwen2.5-Coder-7B-Instruct | GGUF Q4_K_M (Qwen)gguf-q4_k_m · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably4.92 GiB–5.42 GiB | Not available | |
| Qwen2.5-Math-7B-Instruct | GGUF Q4_K_M (bartowski)gguf-q4_k_m · llama.cpp | 4,096 | 4,096 | 8192 Runs comfortably · Rough estimate4.92 GiB–6.23 GiB | Not available | |
| DeepSeek-R1-Distill-Llama-8B | GGUF Q4_K_M (Unsloth)gguf-q4_k_m · llama.cpp | 131,072 | 131,072 | 8192 Runs comfortably5.71 GiB–6.24 GiB | Not available | |
| Llama 3.1 8B Instruct | Official BF16 safetensorsbf16 · vllm | 131,072 | 131,072 | 8192 Runs comfortably16.58 GiB–18.49 GiB | Not available | |
| granite-3.3-8b-instruct | GGUF Q4_K_M (IBM)gguf-q4_k_m · llama.cpp | 131,072 | 131,072 | 8192 Runs comfortably5.98 GiB–6.53 GiB | Not available | |
| Qwen3-8B | GGUF Q4_K_Mgguf-q4_k_m · llama.cpp | 40,960 | 40,960 | 8192 Runs comfortably5.93 GiB–6.48 GiB | Not available | |
| Qwen3-8B-Base | GGUF Q4_K_M (mradermacher)gguf-q4_k_m · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably5.93 GiB–6.48 GiB | Not available | |
| Qwen2.5-VL-7B-Instruct | GGUF Q4_K_M (Unsloth)gguf-q4_k_m · llama.cpp | 128,000 | 128,000 | 8192 Runs comfortably4.92 GiB–5.42 GiB | Not available | |
| Qwen3-VL-8B-Instruct | GGUF Q4_K_M (Qwen)gguf-q4_k_m · llama.cpp | 250,749 | 262,144 | 8192 Runs comfortably5.93 GiB–6.48 GiB | Not available | |
| GLM-4-9B-0414 | GGUF Q4_K_M (Unsloth)gguf-q4_k_m · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably6.18 GiB–6.69 GiB | Not available | |
| Gemma 3 12B IT | GGUF Q4_0 (Google QAT)gguf-q4_0 · llama.cpp | 131,072 | 131,072 | 8192 Runs comfortably8.46 GiB–9.04 GiB | Not available | |
| Mistral-Nemo-Instruct-2407 | GGUF Q4_K_M (Unsloth)gguf-q4_k_m · llama.cpp | 131,072 | 131,072 | 8192 Runs comfortably8.34 GiB–8.94 GiB | Not available | |
| phi-4 | GGUF Q4_K_M (Unsloth)gguf-q4_k_m · llama.cpp | 16,384 | 16,384 | 8192 Runs comfortably9.97 GiB–10.62 GiB | Not available | |
| Phi-4-reasoning | GGUF Q4_K_M (Unsloth)gguf-q4_k_m · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably10.12 GiB–10.77 GiB | Not available | |
| Qwen3-14B | GGUF Q4_K_Mgguf-q4_k_m · llama.cpp | 40,960 | 40,960 | 8192 Runs comfortably9.76 GiB–10.39 GiB | Not available | |
| OpenMath-Nemotron-14B | GGUF Q4_K_M (mradermacher)gguf-q4_k_m · llama.cpp | 131,072 | 131,072 | 8192 Runs comfortably10.00 GiB–10.64 GiB | Not available | |
| Qwen2.5-14B-Instruct | GGUF Q4_K_Mgguf-q4_k_m · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably10.00 GiB–10.64 GiB | Not available | |
| Qwen2.5-Coder-14B-Instruct | GGUF Q4_K_M (Qwen)gguf-q4_k_m · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably10.00 GiB–10.64 GiB | Not available | |
| DeepSeek-V2-Lite-Chat | GGUF Q4_K_M (mradermacher)gguf-q4_k_m · llama.cpp | 163,840 | 163,840 | 8192 Runs comfortably · Rough estimate10.01 GiB–12.23 GiB | Not available | |
| gpt-oss-20b | MXFP4 safetensorsmxfp4 · vllm | 131,072 | 131,072 | 8192 Runs comfortably13.63 GiB–15.51 GiB | Not available | |
| Mistral-Small-24B-Instruct-2501 | GGUF Q4_K_M (Unsloth)gguf-q4_k_m · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably14.72 GiB–15.45 GiB | Not available | |
| Gemma 3 27B IT | GGUF Q4_0 (Google QAT)gguf-q4_0 · llama.cpp | 131,072 | 131,072 | 8192 Runs comfortably17.20 GiB–17.97 GiB | Not available | |
| Qwen3.8-27B | GGUF UD-IQ1_S (Unsloth)gguf-ud-iq1_s · llama.cpp | 262,144 | 262,144 | 8192 Runs comfortably · Rough estimate6.54 GiB–8.14 GiB | Not available | |
| Qwen3-30B-A3B | GGUF Q4_K_Mgguf-q4_k_m · llama.cpp | 40,960 | 40,960 | 8192 Runs comfortably18.16 GiB–18.93 GiB | Not available | |
| Qwen3-30B-A3B-Instruct-2507 | GGUF Q4_K_M (Unsloth)gguf-q4_k_m · llama.cpp | 238,500 | 262,144 | 8192 Runs comfortably18.16 GiB–18.93 GiB | Not available | |
| Qwen3-VL-30B-A3B-Instruct | GGUF Q4_K_M (Qwen)gguf-q4_k_m · llama.cpp | 238,500 | 262,144 | 8192 Runs comfortably18.16 GiB–18.93 GiB | Not available | |
| Qwen3-32B | GGUF Q4_K_Mgguf-q4_k_m · llama.cpp | 40,960 | 40,960 | 8192 Runs comfortably20.53 GiB–21.41 GiB | Not available | |
| DeepSeek-R1-Distill-Qwen-32B | GGUF Q4_K_M (Unsloth)gguf-q4_k_m · llama.cpp | 84,499 | 112,177 | 8192 Runs comfortably20.61 GiB–21.50 GiB | Not available | |
| OpenMath-Nemotron-32B | GGUF Q4_K_M (mradermacher)gguf-q4_k_m · llama.cpp | 84,499 | 112,177 | 8192 Runs comfortably20.61 GiB–21.50 GiB | Not available | |
| Qwen2.5-32B-Instruct | GGUF Q4_K_Mgguf-q4_k_m · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably20.61 GiB–21.50 GiB | Not available | |
| Qwen2.5-Coder-32B-Instruct | GGUF Q4_K_M (Qwen)gguf-q4_k_m · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably20.61 GiB–21.50 GiB | Not available | |
| QwQ-32B | GGUF Q4_K_M (Qwen)gguf-q4_k_m · llama.cpp | 40,960 | 40,960 | 8192 Runs comfortably20.61 GiB–21.50 GiB | Not available | |
| Qwen2.5-VL-32B-Instruct | GGUF Q4_K_M (Unsloth)gguf-q4_k_m · llama.cpp | 84,499 | 112,177 | 8192 Runs comfortably20.61 GiB–21.50 GiB | Not available | |
| Drama 3 | Unofficial int4 W4A16 (GPTQ-Marlin, with codec)int4-w4a16-community · sglang | 262,144 | 262,144 | 8192 Runs comfortably · Rough estimate22.61 GiB–26.64 GiB | Not available | |
| Mixtral-8x7B-Instruct-v0.1 | GGUF Q4_K_M (mradermacher)gguf-q4_k_m · llama.cpp | 32,768 | 32,768 | 8192 Runs comfortably27.62 GiB–28.59 GiB | Not available | |
| Llama-3.1-Nemotron-70B-Instruct-HF | GGUF Q4_K_M (bartowski)gguf-q4_k_m · llama.cpp | 1,631 | 20,561 | 8192 Tight fit42.23 GiB–43.57 GiB | Not available |