FitMyLLM
NVIDIA· Maxwell 2.0

NVIDIA GRID M60-2Q

Running LLMs on the GRID M60-2Q — the long read: which models fit at which quantisation, and the settings worth changing. · Or what a budget buys

VRAM
2 GB
Budget
Bandwidth
160.4
GB/s
Models Q4
48/498
10%
7B Q4 speed
~18
Good
Model coverage at Q410% of all
Estimated speed· By model size at Q4

Average speeds at Q4 quantization. Actual performance varies by model architecture and context length.

3B
—
1.7GB needed
7B
—
3.9GB needed
14B
—
7.9GB needed
32B
—
18.0GB needed
70B
—
39.4GB needed
Measured rig reports

We rent the machine and time every model on it: decode, VRAM peak, concurrency, watts and cost per million tokens. Yours may already be one of them — and two are free to read in full.

See the reports →
Specifications
VRAM
2 GB
Bandwidth
160.4 GB/s
FP16 Compute
4.8 TFLOPS
TDP
225W
Memory
GDDR5
Architecture
Maxwell 2.0
CUDA Cores
2,048
PCIe
Gen 3 x16
48
Fast models · >30 tok/s
Real-time chat speed
48
Usable · >10 tok/s
Comfortable for all tasks
48
Total compatible
Fit in VRAM at Q4
Rent it in the cloud

Buying GRID M60-2Q costs $15–$40k and isn’t practical for most teams. Spin one up by the hour instead:

Spin up in ~60s. Pay by the second. Cancel anytime.

Some links are affiliate links — we may earn a small commission at no extra cost to you. This helps keep FitMyLLM free and independent.

Compatible models· 48
S
Falcon-H1R Tiny 90M0.09B
Falcon·256K ctx· chat· reasoning
1426
tok/s · 27% VRAM
›
S
SmolLM2 135M0.135B
Smollm·2K ctx· chat
951
tok/s · 29% VRAM
›
S
nomic-embed-text-v1.5 100M0.14B
Embedding·8K ctx· chat
917
tok/s · 29% VRAM
›
S
GPT-2 124M0.14B
Gpt2·1K ctx· chat
917
tok/s · 29% VRAM
›
S
SmolVLM 256M0.256B
Smollm·8K ctx· chat· vision
501
tok/s · 32% VRAM
›
S
Gemma 3 270M0.27B
Gemma·32K ctx· chat
475
tok/s · 33% VRAM
›
S
Snowflake Arctic Embed M v2.00.305B
Embedding·8K ctx· embedding· multilingual
421
tok/s · 34% VRAM
›
S
bge-large-en-v1.5 335M0.335B
Embedding·1K ctx· chat
383
tok/s · 35% VRAM
›
S
mxbai-embed-large-v10.335B
Embedding·1K ctx· embedding
383
tok/s · 35% VRAM
›
S
Snowflake Arctic Embed L0.335B
Embedding·1K ctx· embedding
383
tok/s · 35% VRAM
›
S
LFM2 350M0.35B
Lfm·125K ctx· chat· tool_use
367
tok/s · 35% VRAM
›
S
SmolLM2 360M0.36B
Smollm·8K ctx· chat
356
tok/s · 35% VRAM
›
S
GPT-2 Medium 345M0.38B
Gpt2·1K ctx· chat
338
tok/s · 36% VRAM
›
S
Qwen 2.5 0.5B0.5B
Qwen·32K ctx· chat
257
tok/s · 40% VRAM
›
S
SmolVLM 500M0.5B
Smollm·8K ctx· chat· vision
257
tok/s · 40% VRAM
›
S
Falcon-H1 0.5B0.52B
Falcon·128K ctx· chat
247
tok/s · 40% VRAM
›
S
BGE-M30.568B
Embedding·8K ctx· embedding
226
tok/s · 42% VRAM
›
S
Snowflake Arctic Embed L v2.00.568B
Embedding·8K ctx· embedding· multilingual
226
tok/s · 42% VRAM
›
S
Qwen3-Embedding 0.6B0.6B
Embedding·32K ctx· embedding· multilingual
214
tok/s · 43% VRAM
›
S
Falcon-H1R Tiny 0.6B0.6B
Falcon·32K ctx· chat· reasoning
214
tok/s · 43% VRAM
›
S
Falcon Perception 0.6B0.6B
Falcon·4K ctx· vision
214
tok/s · 43% VRAM
›
S
Qwen 1.5 0.5B0.62B
Qwen·32K ctx· chat
207
tok/s · 43% VRAM
›
S
LFM2 700M0.74B
Lfm·125K ctx· chat· tool_use
173
tok/s · 47% VRAM
›
S
Qwen3 0.6B0.75B
Qwen·32K ctx· chat· reasoning
171
tok/s · 47% VRAM
›
S
GPT-2 Large 774M0.81B
Gpt2·1K ctx· chat
158
tok/s · 49% VRAM
›
S
Qwen 3.5 0.8B0.87B
Qwen·256K ctx· chat· coding· multilingual
147
tok/s · 51% VRAM
›
S
InternVL3 1B0.94B
Other·32K ctx· chat· vision
137
tok/s · 53% VRAM
›
S
MiniCPM5 1B1.08B
Minicpm·128K ctx· chat· reasoning· multilingual
119
tok/s · 57% VRAM
›
S
K2 Horizon 0.9B1.08B
Other·128K ctx· chat· coding· reasoning
119
tok/s · 57% VRAM
›
S
TinyLlama 1.1B1.1B
Llama·2K ctx· chat
117
tok/s · 58% VRAM
›
S
LFM2.5-1.2B-Thinking1.2B
Lfm·122K ctx· chat· reasoning· tool_use
107
tok/s · 61% VRAM
›
S
Llama-3.2-1B1.2B
Llama·4K ctx· chat
107
tok/s · 61% VRAM
›
S
LFM2 1.2B1.2B
Lfm·125K ctx· chat· tool_use· multilingual
107
tok/s · 61% VRAM
›
S
Zamba2 1.2B1.2B
Other·4K ctx· chat
107
tok/s · 61% VRAM
›
S
EXAONE-4.0-1.2B1.3B
Exaone·64K ctx· chat
99
tok/s · 64% VRAM
›
S
OPT 1.3B1.3B
Opt·2K ctx· chat
99
tok/s · 64% VRAM
›
S
MiniCPM-V 4.61.3B
Other·256K ctx· chat· vision
99
tok/s · 64% VRAM
›
S
DeepSeek Coder 1.3B1.35B
Deepseek·16K ctx· coding
95
tok/s · 66% VRAM
›
S
Phi-1 1.3B1.42B
Phi·2K ctx· coding
90
tok/s · 68% VRAM
›
S
Phi-1.5 1.3B1.42B
Phi·2K ctx· chat· coding
90
tok/s · 68% VRAM
›
Next step

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your GRID M60-2Q.

What this card is worth

GRID M60-2Q holds 48 of the models in our catalogue and is, in practice, a Q4_K_M card — the largest it takes is LFM3-VL 2B at Q4_K_M.

Tokens/sec per $100
—
8B at Q4_K_M, so cards compare like for like
VRAM per $100
—
what memory costs on this card
The biggest it takes
LFM3-VL 2B1.92B · Q4_K_M1.7 GB87 tok/sest
Moondream2 1.9B1.9B · Q4_K_M1.7 GB88 tok/sest
LFM3 1.7B1.73B · Q6_K1.8 GB72 tok/sest
Falcon3-1B1.67B · Q5_K_M1.8 GB86 tok/sest
LFM2-VL 1.6B1.6B · Q5_K_M1.6 GB90 tok/sest
Falcon-H1 1.5B1.55B · Q6_K1.7 GB81 tok/sest
MiniCPM-V 4.7 1B1.55B · Q5_K_M1.6 GB93 tok/sest
Qwen2.5-Coder-1.5B1.5B · Q6_K1.6 GB83 tok/sest
Against cards of similar memory
M2 (8GB)5 GB$5992.8 tok/s per $100
M3 (8GB)5 GB$5992.8 tok/s per $100
M1 (8GB)5 GB$4992.2 tok/s per $100
RTX 2060 6GB6 GB$15026.7 tok/s per $100
GRID M60-2Q2 GB——

Neighbours in memory rather than in price: memory decides whether a card can do the job at all, so two cards of the same size at different prices is the comparison you are making. Ordered by memory, then bandwidth — not by the value column, which is worked out from bandwidth and price alone and therefore rewards a cheap card whatever its software stack does to that bandwidth in practice. Read it as one input, not as a ranking.

Device under test

NVIDIA GRID M60-2Q — 2 GB VRAM.

GRID M60-2Q spec
Brand
NVIDIA
VRAM
2 GB GDDR5
Bandwidth
160.4 GB/s
FP16 Compute
4.8 TFLOPS
FP32 Compute
4.8 TFLOPS
CUDA Cores
2,048
TDP
225 W
Architecture
Maxwell 2.0
AI capability
48/ 498 models @ Q4

With 2 GB VRAM and 160.4 GB/s bandwidth, this GPU handles models up to 1.61B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~18 tok/s.

Top models for GRID M60-2Q
48 fit · showing 20
ModelSizeVRAM Q4tok/sAvg
GPT-2 XL 1.5B1.61B1.5 GB805.1
stablelm-2-1_6b1.6B1.5 GB809.5
Falcon-H1 1.5B1.55B1.4 GB8343.8
Qwen2.5-Coder-1.5B1.5B1.4 GB8619.6
Qwen2 Math 1.5B1.5B1.4 GB8619.6
Qwen 2.5 1.5B1.5B1.4 GB8630.2
Yi Coder 1.5B1.5B1.4 GB8614.6
Stella en 1.5B v51.5B1.4 GB8652.4
Phi-1 1.3B1.42B1.4 GB907.2
Phi-1.5 1.3B1.42B1.4 GB907.2
DeepSeek Coder 1.3B1.35B1.3 GB9516.8
EXAONE-4.0-1.2B1.3B1.3 GB9922.6
OPT 1.3B1.3B1.3 GB995.3
MiniCPM-V 4.61.3B1.3 GB9928.5
LFM2.5-1.2B-Thinking1.2B1.2 GB10722.3
Llama-3.2-1B1.2B1.2 GB10710.1
LFM2 1.2B1.2B1.2 GB10715.6
Zamba2 1.2B1.2B1.2 GB10741.5
TinyLlama 1.1B1.1B1.2 GB11713.6
MiniCPM5 1B1.08B1.1 GB11930.8