Hardware

CPU only · DDR5-6000

CPU only · DDR5-6000 has 8 / 16 / 32 / 64 / 128 GB System RAM and 96 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

Bandwidth96 GB/s

Kindcpu

Year2024

Dual-channel DDR5-6000: 2 × 6.0 GT/s × 8 bytes = 96 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	11–15
Qwen3.8 35B A3B Distill 35.5B	Runs on CPU	Q5_K_M	8K	23–31
Cyber Tiel Coder 35B A3B GGUF MTP 35.5B	Runs on CPU	Q5_K_M (est.)	8K	23–31
Qwen3.6 35B A3B 34.7B	Runs on CPU	UD-Q5_K_S	8K	23–31
Qwen3.5 35B A3B 34.7B	Runs on CPU	Q5_K_S	8K	23–31
Tiel Coder 35B A3B 34.7B	Runs on CPU	UD-Q4_K_XL	8K	25–34
Nemotron 3 Nano 30B A3B 31.6B	Runs on CPU	Q5_K_S	8K	19–27
NVIDIA Nemotron 3 Nano Omni 30B A3B Reasoning 31.6B	Runs on CPU	UD-Q5_K_S	8K	19–26
Qwen3 Coder 30B A3B Instruct 30.5B	Runs on CPU	Q6_K	8K	16–22
Qwen3 30B A3B Instruct 2507 30.5B	Runs on CPU	Q6_K	8K	16–22
Qwen3 VL 30B A3B Instruct 30.5B	Runs on CPU	Q6_K	8K	16–22
Qwen3 30B A3B Thinking 2507 30.5B	Runs on CPU	Q6_K	8K	16–22
NVIDIA Nemotron 3.5 Lightning 30B A3B 32.9B	Runs on CPU	UD-Q4_K_XL	4K	21–28
bottlecapai ThinkingCap gemma 4 26B A4B it 25.2B	Runs on CPU	Q5_K_M	8K	10–14
Qwen3 Coder Next 79.7B	Runs on CPU	UD-IQ2_XXS	8K	11–15
LFM2.5 24B A2B 24.0B	Runs on CPU	Q8_0	4K	21–29
Qwen3 Next 80B A3B Instruct 79.7B	Runs on CPU	UD-IQ1_M	8K	31–42
Qwen3 Next 80B A3B Thinking 79.7B	Runs on CPU	UD-IQ1_M	8K	31–42
GLM 4.7 Flash REAP 23B A3B 23.0B	Runs on CPU	Q8_0	8K	15–20
gpt oss 20b 20.9B	Runs on CPU	UD-Q8_K_XL	8K	13–18
Qwen3.6 14B A3B FableVibes 13.8B	Runs on CPU	Q8_0	8K	16–21
gemma 4 E4B it qat 7.5B	Runs on CPU	UD-Q4_K_XL	8K	11–15
LFM2.5 8B A1B 8.5B	Runs on CPU	BF16	8K	22–30
Sharp Spark X2.5 4B 4.1B	Runs on CPU	Q6_K	8K	11–15
Qwen3.8 2B Distill 1.9B	Runs on CPU	BF16	8K	13–18
Qwen3.5 2B 1.9B	Runs on CPU	BF16	8K	14–19
Hy MT2 1.8B 1.8B	Runs on CPU	Q8_0	8K	22–29
DeepSeek R1 Distill Qwen 1.5B 1.8B	Runs on CPU	BF16	8K	14–19
Qwen3 1.7B 1.7B	Runs on CPU	BF16	8K	12–16
Qwen3 VL 2B Instruct 1.7B	Runs on CPU	BF16	8K	12–16
Qwen3 VL 2B Thinking 1.7B	Runs on CPU	BF16	8K	12–16
Qwen2.5 1.5B Instruct 1.5B	Runs on CPU	F16	8K	16–22
Qwen2.5 Coder 1.5B Instruct 1.5B	Runs on CPU	F16	8K	16–22
Llama 3.2 1B Instruct 1.2B	Runs on CPU	BF16	8K	19–26
LFM2.5 1.2B Instruct 1.2B	Runs on CPU	BF16	8K	20–28
gemma 3 1b it 1.0B	Runs on CPU	BF16	8K	24–32
Qwen3.5 0.8B 0.75B	Runs on CPU	BF16	8K	33–45
Qwen3 0.6B 0.60B	Runs on CPU	BF16	8K	25–34
Qwen2.5 0.5B Instruct 0.49B	Runs on CPU	F16	8K	48–66
Qwen2.5 32B Instruct 32.8B	Runs on CPU	Q5_K_M	8K	2.1–2.8

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 · DDR5-6000 at Q5_K_M, 8K context, about 11–15 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).