Best local LLMs for tool use

Run open models capable of function calling, designed for agents and apps that use tools and APIs. We rank them using the llmrun Composite Score, offering the top choice for every memory capacity.

Best for tool use on

8 GB 12 GB 16 GB 24 GB 32 GB 48 GB+

Top pick

MiMo V2.6 Pro RL

Xiaomi · Q4_K_M · needs 614 GB · up to 1M context · runs on about 5× H200 SXM 141 GB · from $17.95/hr in the cloud

No memory limit: the best model, whatever memory it needs.

Score

How to run →

All 205 tool-use models, no memory limit ↓

Also worth a look

GLM 5.3

Q4_K_M · needs 454 GB · about 7× H100 SXM 80 GB · 1M ctx

MiMo V2.6 Flash RL

Q4_K_M · needs 187 GB · one B200 192 GB · 1M ctx

Also worth a look

GLM 5.3

Q4_K_M · needs 454 GB · about 7× H100 SXM 80 GB · 1M ctx

Best tool-use model by memory

Highest llmrun Composite Score that fits each size with at least 32K context and 15 t/s, at a Q3 or better quant. Speed is decode tokens per second on that size's reference GPU. The last row has no memory limit: the best model whatever it needs, on the GPU plan shown. Full ranking

8 GB · RTX 5060
Qwen3.5 9B45.8 t/s · 32K ctx
Q4_K_M · 6.6 GB
Runner-up: Gemma 4 E4B IT
12 GB · RTX 5070
Qwen3.5 9B68.7 t/s · 128K ctx
Q4_K_M · 6.6 GB
Runner-up: GPT OSS 20B
16 GB · RTX 5080
Qwen3.8 27B42.6 t/s · 32K ctx
Q4_0 · 15.1 GB
Runner-up: Gemma 4 26B A4B IT
24 GB · RTX 4090
Qwen3.8 27B37.6 t/s · 64K ctx
Q4_K_M · 17.9 GB
Runner-up: Gemma 4 31B IT
32 GB · RTX 5090
Qwen3.8 27B66.9 t/s · 256K ctx
Q4_K_M · 17.9 GB
Runner-up: Gemma 4 31B IT
48 GB+ · no limit · about 5× H200 SXM 141 GB
MiMo V2.6 Pro RL1M ctx
Q4_K_M · needs 614 GB
Runner-up: GLM 5.3

Best tool-use model for each memory size
Memory	Best pick	Speed	Context	Runner-up
8 GBRTX 5060	Qwen3.5 9BQ4_K_M · 6.6 GB	45.8 t/s	32K	Gemma 4 E4B IT54.7 t/s
12 GBRTX 5070	Qwen3.5 9BQ4_K_M · 6.6 GB	68.7 t/s	128K	GPT OSS 20B96.4 · 156.0 t/s
16 GBRTX 5080	Qwen3.8 27BQ4_0 · 15.1 GB	42.6 t/s	32K	Gemma 4 26B A4B IT105.8 · 178.1 t/s
24 GBRTX 4090	Qwen3.8 27BQ4_K_M · 17.9 GB	37.6 t/s	64K	Gemma 4 31B IT106.6 · 32.1 t/s
32 GBRTX 5090	Qwen3.8 27BQ4_K_M · 17.9 GB	66.9 t/s	256K	Gemma 4 31B IT106.6 · 57.1 t/s
48 GB+ · no limitabout 5× H200 SXM 141 GB	MiMo V2.6 Pro RLQ4_K_M · needs 614 GB	n/a	1M	GLM 5.3130.1

Tool-use models, no memory limit205

Ranked by Composite Score, models without one after. Memory is what the listed quant needs; speed is shown only for models that fit one 48 GB GPU.

205 models

Featured only

Score: llmrun Score, 100 = average model. Ordered by Score. How ranking works

LLM models ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context
GLM 4.5358.3BChatFunctions Q4_K_M·—	Q4_K_M	217.9 GB	—	131K
Qwen3 30B A3B Thinking 250730.5BChatFunctions Q4_K_M·168.5 t/s	Q4_K_M	19.4 GB	168.5 t/s	262K
DeepSeek V3.1684.5BChatFunctions Q4_K_M·—	Q4_K_M	412.2 GB	—	164K
Kimi K2 Instruct1026.4BChatFunctions Q4_K_M·—	Q4_K_M	617.3 GB	—	131K
Qwen3 235B A22B235.1BChatFunctions Q4_K_M·—	Q4_K_M	142.9 GB	—	41K
Qwen3.5 9B9.7BVisionFunctions Q4_K_M·98.1 t/s	Q4_K_M	6.6 GB	98.1 t/s	262K
DeepSeek R1684.5BChatReasoningFunctions Q4_K_M·—	Q4_K_M	412.1 GB	—	164K
Qwen3 32B32.8BChatFunctions Q4_K_M·30.8 t/s	Q4_K_M	22.6 GB	30.8 t/s	41K
GLM 4.5 Air110.5BChatFunctions Q4_K_M·—	Q4_K_M	67.6 GB	—	131K
Qwen3 235B A22B Instruct 2507235.1BChatFunctions Q4_K_M·—	Q4_K_M	142.9 GB	—	262K
Qwen3 14B14.8BChatFunctions Q4_K_M·65.7 t/s	Q4_K_M	11.8 GB	65.7 t/s	41K
GPT OSS 120B116.8BChatFunctions Q4_K_M·—	Q4_K_M	70.8 GB	—	131K
DeepSeek R1 Distill Qwen 32B32.8BChatReasoningFunctions Q4_K_M·30.4 t/s	Q4_K_M	24.3 GB	30.4 t/s	131K
Qwen3 30B A3B Instruct 250730.5BChatFunctions Q4_K_M·168.5 t/s	Q4_K_M	19.4 GB	168.5 t/s	262K
GPT OSS 20B20.9BChatFunctions Q4_K_M·182.8 t/s	Q4_K_M	13.1 GB	182.8 t/s	131K

How much memory do you need for a tool-use model?

From 8 to 12 GB the best tool-use model is Qwen3.5 9B (score 99). From 16 to 32 GB it is Qwen3.8 27B (score 122). With no memory limit, the best is MiMo V2.6 Pro RL (score 133). Since agents pass lengthy prompts packed with tool definitions and outcomes, both context window size and processing speed matter. Choose a model that retains a generous amount of context within its memory.

Frequently Asked Questions

What is the best local LLM for tool use?

On 24 GB, Qwen3.8 27B is the top pick with a score of 122, running at about 38 t/s on RTX 4090. It fits up to 64K tokens of context there. On 8 GB, the best fit is Qwen3.5 9B. With no memory limit, the best is MiMo V2.6 Pro RL. Open a model to see which GPUs and Macs run it.

Can I run a tool-use model on a laptop or an 8 GB GPU?

Yes. On 8 GB the best pick is Qwen3.5 9B (Q4_K_M, 6.6 GB), which runs at about 46 t/s on RTX 5060. Laptops with 8 to 16 GB of memory can run smaller models in the same way.

What is tool calling?

Instead of plain text, the model outputs a structured call like a function name plus its arguments. Your code executes that function, sends back the result, and lets the model continue from there.

Which runtime supports tool calling for local models?

Ollama, LM Studio, llama.cpp, and vLLM all offer an OpenAI-compatible tools interface for models built to use it. Remember that the model's chat template needs to support these tools.