FitMyLLM
▸ NVIDIA· TESLA

NVIDIA GeForce 9600 GT Mac Edition

Running LLMs on the GeForce 9600 GT Mac Edition — the long read: which models fit at which quantisation, and the settings worth changing. · Or what a budget buys

VRAM
1 GB
BUDGET
BANDWIDTH
17
GB/S
MODELS Q4
4/449
1%
7B Q4 SPEED
~2
SLOW
▸ MODEL COVERAGE @ Q41% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ 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
1 GB
BANDWIDTH
17 GB/s
FP16 COMPUTE
0.2 TFLOPS
TDP
95W
MEMORY
DDR2
ARCHITECTURE
Tesla
CUDA CORES
64
PCIE
Gen 2 x16
4
FAST MODELS · >30 TOK/S
Real-time chat speed
4
USABLE · >10 TOK/S
Comfortable for all tasks
4
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test GeForce 9600 GT Mac Edition (or anything bigger) without committing. Pay by the second, cancel anytime.

Rent on Vast.ai →Or RunPod →

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· 4
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
151
TOK/S · 54% VRAM
›
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
101
TOK/S · 57% VRAM
›
S
nomic-embed-text-v1.5 100M0.14B
EMBEDDING·8K CTX· CHAT
97
TOK/S · 57% VRAM
›
S
GPT-2 124M0.14B
GPT2·1K CTX· CHAT
97
TOK/S · 57% VRAM
›
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your GeForce 9600 GT Mac Edition.

▸Find models for GeForce 9600 GT Mac EditionCompare with other GPUs
WHAT THIS CARD IS WORTH

9600 GT Mac Edition holds 4 of the models in our catalogue and is, in practice, a Q4_K_M card — the largest it takes is Qwen 3.5 0.8B 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
Qwen 3.5 0.8B0.87B · Q4_K_M0.9 GB24 tok/sEST
LFM2 700M0.74B · Q4_K_M0.9 GB28 tok/sEST
Falcon-H1R Tiny 0.6B0.6B · Q6_K0.9 GB26 tok/sEST
Falcon Perception 0.6B0.6B · Q5_K_S0.9 GB31 tok/sEST
Falcon-H1 0.5B0.52B · Q6_K0.8 GB30 tok/sEST
Qwen 2.5 0.5B0.5B · Q8_00.9 GB24 tok/sEST
SmolVLM 500M0.5B · Q6_K0.9 GB31 tok/sEST
SmolLM2 360M0.36B · Q8_00.8 GB33 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
Radeon RX 6600S4 GB$175—
9600 GT Mac Edition1 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 GeForce 9600 GT Mac Edition — 1 GB VRAM.

▸ GEFORCE 9600 GT MAC EDITION SPEC
BRAND
NVIDIA
VRAM
1 GB DDR2
BANDWIDTH
17 GB/s
FP16 COMPUTE
0.2 TFLOPS
FP32 COMPUTE
0.2 TFLOPS
CUDA CORES
64
TDP
95 W
ARCHITECTURE
Tesla
▸ AI CAPABILITY
4/ 449 models @ Q4

With 1 GB VRAM and 17 GB/s bandwidth, this GPU handles models up to 0.14B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~2 tok/s.

§ 01TOP MODELS FOR GEFORCE 9600 GT MAC EDITION
4 FIT · SHOWING 4
MODELSIZEVRAM Q4TOK/SAVG
nomic-embed-text-v1.5 100M0.14B0.6 GB9762.3
GPT-2 124M0.14B0.6 GB976.5
SmolLM2 135M0.135B0.6 GB1017.0
Falcon-H1R Tiny 90M0.09B0.5 GB151—