Hardware

CPU only · DDR5-5600

CPU only · DDR5-5600 has 8 / 16 / 32 / 64 / 128 GB System RAM and 89.6 GB/s. See which open models fit, at which quant, and roughly how fast. Figures below use the default memory (32 GB). Updated 2026-10-24.

Memory8 / 16 / 32 / 64 / 128 GB System RAM

Bandwidth89.6 GB/s

Kindcpu

Year2024

Dual-channel DDR5-5600: 2 × 5.6 GT/s × 8 bytes = 89.6 GB/s. Source.

RSS for new models on this device

Models that fit

Model	Verdict	Quant	Context	tok/s
Kwaipilot KAT Coder V2.5 Dev 34.7B	Runs on CPU	Q5_K_M	8K	10–14
Qwen3.8 35B A3B Distill 35.5B	Runs on CPU	Q5_K_M	8K	21–29
Cyber Tiel Coder 35B A3B GGUF MTP 35.5B	Runs on CPU	Q5_K_M (est.)	8K	21–29
Qwen3.6 35B A3B 34.7B	Runs on CPU	UD-Q5_K_S	8K	21–29
Qwen3.5 35B A3B 34.7B	Runs on CPU	Q5_K_S	8K	21–29
Tiel Coder 35B A3B 34.7B	Runs on CPU	UD-Q4_K_XL	8K	23–32
Nemotron 3 Nano 30B A3B 31.6B	Runs on CPU	Q5_K_S	8K	18–25
NVIDIA Nemotron 3 Nano Omni 30B A3B Reasoning 31.6B	Runs on CPU	UD-Q5_K_S	8K	18–24
Qwen3 Coder 30B A3B Instruct 30.5B	Runs on CPU	Q6_K	8K	15–21
Qwen3 30B A3B Instruct 2507 30.5B	Runs on CPU	Q6_K	8K	15–21
Qwen3 VL 30B A3B Instruct 30.5B	Runs on CPU	Q6_K	8K	15–21
Qwen3 30B A3B Thinking 2507 30.5B	Runs on CPU	Q6_K	8K	15–21
NVIDIA Nemotron 3.5 Lightning 30B A3B 32.9B	Runs on CPU	UD-Q4_K_XL	4K	19–26
bottlecapai ThinkingCap gemma 4 26B A4B it 25.2B	Runs on CPU	Q5_K_M	8K	9.5–13
Qwen3 Coder Next 79.7B	Runs on CPU	UD-IQ2_XXS	8K	10–14
LFM2.5 24B A2B 24.0B	Runs on CPU	Q8_0	4K	20–27
Qwen3 Next 80B A3B Instruct 79.7B	Runs on CPU	UD-IQ1_M	8K	29–39
Qwen3 Next 80B A3B Thinking 79.7B	Runs on CPU	UD-IQ1_M	8K	29–39
GLM 4.7 Flash REAP 23B A3B 23.0B	Runs on CPU	Q8_0	8K	14–18
gpt oss 20b 20.9B	Runs on CPU	UD-Q8_K_XL	8K	12–17
Qwen3.6 14B A3B FableVibes 13.8B	Runs on CPU	Q8_0	8K	15–20
gemma 4 E4B it qat 7.5B	Runs on CPU	UD-Q4_K_XL	8K	10–14
LFM2.5 8B A1B 8.5B	Runs on CPU	BF16	8K	20–28
Sharp Spark X2.5 4B 4.1B	Runs on CPU	Q6_K	8K	10–14
Qwen3.8 2B Distill 1.9B	Runs on CPU	BF16	8K	12–17
Qwen3.5 2B 1.9B	Runs on CPU	BF16	8K	13–17
Hy MT2 1.8B 1.8B	Runs on CPU	Q8_0	8K	20–27
DeepSeek R1 Distill Qwen 1.5B 1.8B	Runs on CPU	BF16	8K	13–18
Qwen3 1.7B 1.7B	Runs on CPU	BF16	8K	11–15
Qwen3 VL 2B Instruct 1.7B	Runs on CPU	BF16	8K	11–15
Qwen3 VL 2B Thinking 1.7B	Runs on CPU	BF16	8K	11–15
Qwen2.5 1.5B Instruct 1.5B	Runs on CPU	F16	8K	15–20
Qwen2.5 Coder 1.5B Instruct 1.5B	Runs on CPU	F16	8K	15–20
Llama 3.2 1B Instruct 1.2B	Runs on CPU	BF16	8K	18–24
LFM2.5 1.2B Instruct 1.2B	Runs on CPU	BF16	8K	19–26
gemma 3 1b it 1.0B	Runs on CPU	BF16	8K	22–30
Qwen3.5 0.8B 0.75B	Runs on CPU	BF16	8K	30–42
Qwen3 0.6B 0.60B	Runs on CPU	BF16	8K	23–31
Qwen2.5 0.5B Instruct 0.49B	Runs on CPU	F16	8K	45–61
Qwen2.5 32B Instruct 32.8B	Runs on CPU	Q5_K_M	8K	1.9–2.6

105 more models in the catalog do not fit this default profile, or ranked below the first 40 that do.

Example: Runs on CPU on your CPU only · DDR5-5600 at Q5_K_M, 8K context, about 10–14 tok/s. Weights 23.3 GB plus 0.19 GB of KV cache — 24.0 GB of 25.2 GB usable. Up to 32K context still fits. Weights shown in the verdict use GiB (the same 1024³ counting as GPU memory).