Which local LLMs can the DDR4-3200 dual-channel CPU run?

No GPU — the whole model runs from system RAM

CPU-only inference with 4 GB of RAM kept for the OS, 8k context and an f16 KV cache. Verdicts are shown for each RAM size.

Specs

Memory options: 16 GB · 32 GB · 64 GB
Memory bandwidth: 51.2 GB/s
Launch year: 2016

Verdicts at a glance

At Q4_K_M (or the closest available quant) with 8k context.

16 GBRuns great0 modelsRuns well0 modelsRuns slowly11 modelsWon't run18 models3 more models run at a lower quant.
32 GBRuns great0 modelsRuns well0 modelsRuns slowly15 modelsWon't run14 models3 more models run at a lower quant.
64 GBRuns great0 modelsRuns well0 modelsRuns slowly15 modelsWon't run14 models5 more models run at a lower quant.

How to read the verdicts

Runs great: Fully on the GPU at 20 tok/s or more
Runs well: Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
Runs slowly: 2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
Won't run: Does not fit, or under 2 tok/s

Every model on the DDR4-3200 dual-channel CPU

Scroll sideways to see every column.

29 models sorted by verdict and speed, with 64 GB of memory
Model	Verdict	Speed	Quant	Memory	Runs as	Context	Notes
EXAONE 4.0 1.2B	Runs slowly	est. 19.5 tok/s15.6–23.4calibrated estimate ±20%	Q4_K_M	1.3 GB RAM	CPU only	up to 64k	CPU inference — capped at Runs slowly
HyperCLOVA X SEED 1.5B	Runs slowly	est. 14.1 tok/s11.3–16.9calibrated estimate ±20%	Q4_K_M	1.8 GB RAM	CPU only	up to 16k	CPU inference — capped at Runs slowly
Qwen3.5 35B-A3B	Runs slowly	est. 10.7 tok/s8.6–12.8calibrated estimate ±20%	Q4_K_M	22.8 GB RAM	CPU only	up to 256k	CPU inference — capped at Runs slowly
gpt-oss-20b	Runs slowly	est. 9.6 tok/s7.7–11.6calibrated estimate ±20%	MXFP4	12.3 GB RAM	CPU only	up to 128k	reasoning model
Qwen3 30B-A3B (2507)	Runs slowly	est. 7.8 tok/s6.3–9.4calibrated estimate ±20%	Q4_K_M	19.4 GB RAM	CPU only	up to 64k	—
Gemma 4 26B-A4B	Runs slowly	est. 7.6 tok/s6.1–9.1calibrated estimate ±20%	Q4_K_M	17.3 GB RAM	CPU only	up to 128k	—
Kanana 1.5 15.7B-A3B	Runs slowly	est. 7.2 tok/s5.7–8.6calibrated estimate ±20%	Q4_K_M	11.5 GB RAM	CPU only	up to 32k	—
DeepSeek R1 Distill Llama 8B	Runs slowly	est. 4.3 tok/s3.4–5.1calibrated estimate ±20%	Q4_K_M	6.0 GB RAM	CPU only	up to 16k	reasoning model
Kanana 1.5 8B	Runs slowly	est. 4.3 tok/s3.4–5.1calibrated estimate ±20%	Q4_K_M	6.0 GB RAM	CPU only	up to 32k	—
Llama 3.1 8B	Runs slowly	est. 4.3 tok/s3.4–5.1calibrated estimate ±20%	Q4_K_M	6.0 GB RAM	CPU only	up to 32k	—
Qwen3.5 9B	Runs slowly	est. 4.2 tok/s3.3–5.0calibrated estimate ±20%	Q4_K_M	6.1 GB RAM	CPU only	up to 128k	—
Qwen3 8B	Runs slowly	est. 4.1 tok/s3.3–4.9calibrated estimate ±20%	Q4_K_M	6.2 GB RAM	CPU only	up to 32k	—
Gemma 4 12B	Runs slowly	est. 3.3 tok/s2.7–4.0calibrated estimate ±20%	Q4_K_M	7.7 GB RAM	CPU only	up to 64k	—
Gemma 3 12B	Runs slowly	est. 3.3 tok/s2.6–3.9calibrated estimate ±20%	Q4_K_M	7.8 GB RAM	CPU only	up to 64k	—
Qwen3 14B	Runs slowly	est. 2.5 tok/s2.0–3.0calibrated estimate ±20%	Q4_K_M	10.3 GB RAM	CPU only	up to 16k	—
Qwen3.5 122B-A10B	Won't runTry UD-Q2_K_XL (heavy quality loss): Runs slowly	est. 6.1 tok/s4.9–7.3calibrated estimate ±20%	UD-Q2_K_XL	43.1 GB RAM	CPU only	up to 256k	—
Solar Open 100B	Won't runTry IQ4_XS: Runs slowly	est. 2.7 tok/s2.2–3.3calibrated estimate ±20%	IQ4_XS	57.1 GB RAM	CPU only	up to 16k	—
HyperCLOVA X SEED Think 14B	Won't run	est. 2.5 tok/s1.8–3.3theoretical estimate ±30%	Q4_K_M	10.2 GB RAM	CPU only	—	Fits, but too slow to use reasoning model
Mistral Small 3.2 24B	Won't runTry Q2_K (heavy quality loss): Runs slowly	est. 2.5 tok/s2.0–3.0calibrated estimate ±20%	Q2_K	10.2 GB RAM	CPU only	up to 16k	—
Phi-4	Won't run	est. 2.4 tok/s1.9–2.9calibrated estimate ±20%	Q4_K_M	10.7 GB RAM	CPU only	—	Fits, but too slow to use reasoning model
Gemma 3 27B	Won't runTry Q2_K (heavy quality loss): Runs slowly	est. 2.3 tok/s1.8–2.7calibrated estimate ±20%	Q2_K	11.2 GB RAM	CPU only	up to 16k	—
Qwen3.5 27B	Won't runTry UD-Q2_K_XL (heavy quality loss): Runs slowly	est. 2.0 tok/s1.6–2.4calibrated estimate ±20%	UD-Q2_K_XL	12.6 GB RAM	CPU only	up to 8k	—
EXAONE 4.0 32B	Won't run	est. 1.3 tok/s1.0–1.5calibrated estimate ±20%	Q4_K_M	19.9 GB RAM	CPU only	—	Fits, but too slow to use reasoning model
EXAONE 4.5 33B	Won't run	est. 1.2 tok/s1.0–1.5calibrated estimate ±20%	Q4_K_M	20.6 GB RAM	CPU only	—	Fits, but too slow to use reasoning model
Qwen3 32B	Won't run	est. 1.2 tok/s0.9–1.4calibrated estimate ±20%	Q4_K_M	21.9 GB RAM	CPU only	—	Fits, but too slow to use
DeepSeek R1 Distill Qwen 32B	Won't run	est. 1.2 tok/s0.9–1.4calibrated estimate ±20%	Q4_K_M	22.0 GB RAM	CPU only	—	Fits, but too slow to use reasoning model
Llama 3.3 70B	Won't run	est. 0.6 tok/s0.5–0.7calibrated estimate ±20%	Q4_K_M	45.2 GB RAM	CPU only	—	Fits, but too slow to use
gpt-oss-120b	Won't run	—	MXFP4	needs 63.7 GB	—	—	Needs about 63.7 GB; 60.0 GB of RAM is free reasoning model
Solar Open 2 250B	Won't run	—	IQ4_XS	needs 136.6 GB	—	—	Needs about 136.6 GB; 60.0 GB of RAM is free

Reasoning models spend extra tokens thinking, so their speed thresholds are 1.5× stricter (30 / 12 / 3 tok/s).

Verdict by memory size

Q4_K_M verdict for each memory configuration — open the model page for speeds
Model	16 GB	32 GB	64 GB
EXAONE 4.0 1.2B	Runs slowly	Runs slowly	Runs slowly
HyperCLOVA X SEED 1.5B	Runs slowly	Runs slowly	Runs slowly
Qwen3.5 35B-A3B	Won't run	Runs slowly	Runs slowly
gpt-oss-20b	Won't run	Runs slowly	Runs slowly
Qwen3 30B-A3B (2507)	Won't run	Runs slowly	Runs slowly
Gemma 4 26B-A4B	Won't run	Runs slowly	Runs slowly
Kanana 1.5 15.7B-A3B	Runs slowly	Runs slowly	Runs slowly
DeepSeek R1 Distill Llama 8B	Runs slowly	Runs slowly	Runs slowly
Kanana 1.5 8B	Runs slowly	Runs slowly	Runs slowly
Llama 3.1 8B	Runs slowly	Runs slowly	Runs slowly
Qwen3.5 9B	Runs slowly	Runs slowly	Runs slowly
Qwen3 8B	Runs slowly	Runs slowly	Runs slowly
Gemma 4 12B	Runs slowly	Runs slowly	Runs slowly
Gemma 3 12B	Runs slowly	Runs slowly	Runs slowly
Qwen3 14B	Runs slowly	Runs slowly	Runs slowly
Qwen3.5 122B-A10B	Won't run	Won't run	Won't run
Solar Open 100B	Won't run	Won't run	Won't run
HyperCLOVA X SEED Think 14B	Won't run	Won't run	Won't run
Mistral Small 3.2 24B	Won't run	Won't run	Won't run
Phi-4	Won't run	Won't run	Won't run
Gemma 3 27B	Won't run	Won't run	Won't run
Qwen3.5 27B	Won't run	Won't run	Won't run
EXAONE 4.0 32B	Won't run	Won't run	Won't run
EXAONE 4.5 33B	Won't run	Won't run	Won't run
Qwen3 32B	Won't run	Won't run	Won't run
DeepSeek R1 Distill Qwen 32B	Won't run	Won't run	Won't run
Llama 3.3 70B	Won't run	Won't run	Won't run
gpt-oss-120b	Won't run	Won't run	Won't run
Solar Open 2 250B	Won't run	Won't run	Won't run

Measured results on the DDR4-3200 dual-channel CPU

No public measurements for this device yet.

Frequently asked questions

What is the largest model this CPU setup can run?

Solar Open 100B at IQ4_XS (a 55.53 GB file) runs from 64 GB of RAM at est. 2.7 tok/s (2.2–3.3, calibrated estimate ±20%).

How many local LLMs run well on the DDR4-3200 dual-channel CPU?

At Q4_K_M with 8k context, with 64 GB of memory, out of 29 tracked models: 0 run great, 0 run well, 15 run slowly and 14 won't run.

Can the DDR4-3200 dual-channel CPU run a 70B model like Llama 3.3 70B?

It fits in memory but is too slow to use: est. 0.6 tok/s (0.5–0.7, calibrated estimate ±20%).

Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.